OpenAI is scary and wonderful. With the prompt Describe the differences in elections to Holyrood and Westminster, I got
There are a few key differences between elections to Holyrood and Westminster. Firstly, the voting system used in Scottish Parliament elections is proportional representation, whereas Westminster uses first-past-the-post. This means that the number of seats a party wins in Holyrood is more closely aligned with the percentage of the vote they receive, whereas a party can win a majority of seats in Westminster with only a small percentage of the vote.
Another key difference is that the Scottish Parliament has a much greater degree of devolved power than the Westminster Parliament. This means that the Scottish Parliament can pass its own laws on a range of issues, whereas Westminster is limited to passing laws that apply to the whole of the UK.
Finally, the Scottish Parliament is unicameral, meaning that it has only one chamber (the House of Commons), whereas Westminster has two (the House of Commons and the House of Lords).
It's a bit weird, to be sure. I'd quibble over "small percentage" but it IS plugged into an important point. The bit about "much greater degree" is frankly very "AI"... a human who understood this subject wouldn't have said that. And the whole thing drifts a little off point (I was asking about elections, not powers, and the point about unicamerality needs a little more work to bring it to the point about elections versus appointments).
But that is a spectacular answer for a machine. I'm 100% certain that it's a better answer than I would have gotten from several people on here if I'd asked the question.
It would still get zero though:
1) Holyrood isn't elected by PR, but by the AM system using the D'Hondt method;
2) it has the law making powers issue backwards. The Westminster Parliament can pass laws on anything it likes, but the Scottish Parliament has limits on its authority, set by Westminster;
3) The unicameral Scottish Parliament isn't called 'the House of Commons.'
4) As you note, most of it doesn't even ATQ.
It's elegantly expressed nonsense, but it's still nonsense.
So, in my experience at least, just like the answers of most GCSE candidates then?
I always have to remind them: RTFQ.
No argument from me. I had to mark an answer this week that tried to convince me democracy wasn't a great system of government because Athens attacked Sparta. OK, so it augured a wealth of knowledge that would have set @Leon purring, but it wasn't really relevant to twenty-first century British politics.
My old maths teacher used to write TBNH on parts of my proofs when I got lost: true, but not helpful.
Any thoughts (tips) about the Grand National today team?
Tips for the Grand National?
1. Don’t bet on a 4m4f, 40-horse handicapped steeplechase?
In the 80s I worked in a large office. I would collect money from everyone an go down to the bookies and back the worst horse in the race. The main joy was the panic it caused. It normally involved a phone call being made before the bet was taken. Once they were reassured they were taking the bet from a nutter all was good.
Most years our horse would be last seen eating the privet from the first jump. But one year Double You Again was leading very close to the end before being taken out by a riderless horse that refused to jump.
Documents seen by The Independent show trusts linked to Ms Murty, her family and companies linked to their businesses. In a number of them, Mr Sunak was listed as a beneficiary.
Wow, when her tax affairs first were reported I (a frothing at the mouth tax the rich until their pips squeak left-winger) didn't see what the issue was and felt that the "anger" totally confected.
Now.... now Sunak is showing all the sure foot of a blind arthritic elephant in a over crowded china shop.
The sad thing about this story is the emnity towards wealthy and successful people. There is no smoking gun here at all. Everything they have done is entirely legal. Being listed as a 'beneficiary' in a Cayman Islands trust.... so what.
If you don't like non dom status.... then scrap it. But if it is there, you cannot blame people for using it. And the expectation that she has somehow a greater obligation to Britain than anyone elses wife, is laughable. There are lots of international marriages going on; it is an inevitable consequence of globalisation. People are just projecting their own ideas about marriage - largely from a different age.... on to the Sunaks.
We have a shortage of sane and competent people going in to politics. These are the people that we elect to run the country. Why not have someone who is has been successful and is independently wealthy.... I don't see the problem. I have never been a particular fan of Sunak, but if he is hounded out over this it would be a bad loss.
The end point, is that no one successful, goes in to politics.... and we are nearly there already. We will just get a bunch of activists. We end up with Jared O'Mara 2; over and over again.
I mostly agree. From my left-wing position I think that frothing over individuals taking advantage of a deliberately-created loophole is a distraction and unfair as well. Change the system so that it rewards people for doing what we want - making nondom status vastly more expensive would be a start, so that in the end it's usually more sensible just to pay tax in the country where you live..
Decent people don't need rules to force them to do the right thing. If it doesn't feel right don't do it.
As Judge Learned Hand famously said:
Over and over again courts have said that there is nothing sinister in so arranging one's affairs as to keep taxes as low as possible. Everybody does so, rich or poor; and all do right, for nobody owes any public duty to pay more than the law demands: taxes are enforced exactions, not voluntary contributions. To demand more in the name of morals is mere cant.
Not everything is black and white. In fact few things are. Taxation like claiming expenses are broad brushstrokes. It's the attitude of Lord Hand that leads to MP's claiming duck ponds on expenses because no one told them they shouldn't be.
Who claimed for a duck pond?
I think you're thinking of Sir Peter Viggers and the duck house:
When Cameron was told about this, his first words were apparently, 'what the fuck is a duck house?'
Not sure if that was fury, horror or ignorance...
Quite. I remembered the duck house, I was wondering why @Roger thought there was a duck pond.
I'm sure all MPs dream of making an indelible mark on UK politics such that for decades a single phrase is sufficient to recall them in conversation. "Duck house."
He’s a politician not a comedian . I’d rather have wooden than a pathological liar .
Although, speaking as somebody who would infinitely prefer Starmer to Johnson, we need to be careful about the integrity comparisons. Starmer is a QC and ex-DPP.
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
What's the case for limiting it to the Grand National, if you take that view?
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki) Horse Deaths at Cheltenham Festival: 73 (Wiki) Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
OpenAI is scary and wonderful. With the prompt Describe the differences in elections to Holyrood and Westminster, I got
There are a few key differences between elections to Holyrood and Westminster. Firstly, the voting system used in Scottish Parliament elections is proportional representation, whereas Westminster uses first-past-the-post. This means that the number of seats a party wins in Holyrood is more closely aligned with the percentage of the vote they receive, whereas a party can win a majority of seats in Westminster with only a small percentage of the vote.
Another key difference is that the Scottish Parliament has a much greater degree of devolved power than the Westminster Parliament. This means that the Scottish Parliament can pass its own laws on a range of issues, whereas Westminster is limited to passing laws that apply to the whole of the UK.
Finally, the Scottish Parliament is unicameral, meaning that it has only one chamber (the House of Commons), whereas Westminster has two (the House of Commons and the House of Lords).
It's a bit weird, to be sure. I'd quibble over "small percentage" but it IS plugged into an important point. The bit about "much greater degree" is frankly very "AI"... a human who understood this subject wouldn't have said that. And the whole thing drifts a little off point (I was asking about elections, not powers, and the point about unicamerality needs a little more work to bring it to the point about elections versus appointments).
But that is a spectacular answer for a machine. I'm 100% certain that it's a better answer than I would have gotten from several people on here if I'd asked the question.
It would still get zero though:
1) Holyrood isn't elected by PR, but by the AM system using the D'Hondt method;
2) it has the law making powers issue backwards. The Westminster Parliament can pass laws on anything it likes, but the Scottish Parliament has limits on its authority, set by Westminster;
3) The unicameral Scottish Parliament isn't called 'the House of Commons.'
4) As you note, most of it doesn't even ATQ.
It's elegantly expressed nonsense, but it's still nonsense.
Yeah, wheenver you see a "AI generated" article that actually reads coherently and is accurate there's always a footnote somewhere saying something along the lines of "This article was produced by generating 8 runs of the AI and a human editor constructed the final piece"
OpenAI is scary and wonderful. With the prompt Describe the differences in elections to Holyrood and Westminster, I got
There are a few key differences between elections to Holyrood and Westminster. Firstly, the voting system used in Scottish Parliament elections is proportional representation, whereas Westminster uses first-past-the-post. This means that the number of seats a party wins in Holyrood is more closely aligned with the percentage of the vote they receive, whereas a party can win a majority of seats in Westminster with only a small percentage of the vote.
Another key difference is that the Scottish Parliament has a much greater degree of devolved power than the Westminster Parliament. This means that the Scottish Parliament can pass its own laws on a range of issues, whereas Westminster is limited to passing laws that apply to the whole of the UK.
Finally, the Scottish Parliament is unicameral, meaning that it has only one chamber (the House of Commons), whereas Westminster has two (the House of Commons and the House of Lords).
It's a bit weird, to be sure. I'd quibble over "small percentage" but it IS plugged into an important point. The bit about "much greater degree" is frankly very "AI"... a human who understood this subject wouldn't have said that. And the whole thing drifts a little off point (I was asking about elections, not powers, and the point about unicamerality needs a little more work to bring it to the point about elections versus appointments).
But that is a spectacular answer for a machine. I'm 100% certain that it's a better answer than I would have gotten from several people on here if I'd asked the question.
It would still get zero though:
1) Holyrood isn't elected by PR, but by the AM system using the D'Hondt method;
2) it has the law making powers issue backwards. The Westminster Parliament can pass laws on anything it likes, but the Scottish Parliament has limits on its authority, set by Westminster;
3) The unicameral Scottish Parliament isn't called 'the House of Commons.'
4) As you note, most of it doesn't even ATQ.
It's elegantly expressed nonsense, but it's still nonsense.
So, in my experience at least, just like the answers of most GCSE candidates then?
I always have to remind them: RTFQ.
No argument from me. I had to mark an answer this week that tried to convince me democracy wasn't a great system of government because Athens attacked Sparta. OK, so it augured a wealth of knowledge that would have set @Leon purring, but it wasn't really relevant to twenty-first century British politics.
There was this one idiot a few weeks ago who said that when the Roman Empire fell "it was largely as a result of uncontrolled immigration"...
Well, that's one possible way of looking at it I suppose, but I would argue anyone suggesting that as a parallel is being a Vandal.
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
Animals died to make the saddles for the horses (I assume they are still leather), so a few dying more visibly isn’t something that bothers me too much.
Mind you, I’m a farmer’s son, so I have a less romantic view of animals than many seem to.
Well, I would quibble there, as I've heard a few stories about sheep farmers...
I have a dim memory of reading about the outbreak of a certain equine venereal disease in the Newmarket area, in the human population. TBF I have no idea if it could also be acquired through skin abrasions/bites etc.
You do not want to get bitten by a horse in any part of your anatomy, let alone one that leads to a Venetian disease…
OpenAI is scary and wonderful. With the prompt Describe the differences in elections to Holyrood and Westminster, I got
There are a few key differences between elections to Holyrood and Westminster. Firstly, the voting system used in Scottish Parliament elections is proportional representation, whereas Westminster uses first-past-the-post. This means that the number of seats a party wins in Holyrood is more closely aligned with the percentage of the vote they receive, whereas a party can win a majority of seats in Westminster with only a small percentage of the vote.
Another key difference is that the Scottish Parliament has a much greater degree of devolved power than the Westminster Parliament. This means that the Scottish Parliament can pass its own laws on a range of issues, whereas Westminster is limited to passing laws that apply to the whole of the UK.
Finally, the Scottish Parliament is unicameral, meaning that it has only one chamber (the House of Commons), whereas Westminster has two (the House of Commons and the House of Lords).
It's a bit weird, to be sure. I'd quibble over "small percentage" but it IS plugged into an important point. The bit about "much greater degree" is frankly very "AI"... a human who understood this subject wouldn't have said that. And the whole thing drifts a little off point (I was asking about elections, not powers, and the point about unicamerality needs a little more work to bring it to the point about elections versus appointments).
But that is a spectacular answer for a machine. I'm 100% certain that it's a better answer than I would have gotten from several people on here if I'd asked the question.
It would still get zero though:
1) Holyrood isn't elected by PR, but by the AM system using the D'Hondt method;
2) it has the law making powers issue backwards. The Westminster Parliament can pass laws on anything it likes, but the Scottish Parliament has limits on its authority, set by Westminster;
3) The unicameral Scottish Parliament isn't called 'the House of Commons.'
4) As you note, most of it doesn't even ATQ.
It's elegantly expressed nonsense, but it's still nonsense.
So, in my experience at least, just like the answers of most GCSE candidates then?
I always have to remind them: RTFQ.
No argument from me. I had to mark an answer this week that tried to convince me democracy wasn't a great system of government because Athens attacked Sparta. OK, so it augured a wealth of knowledge that would have set @Leon purring, but it wasn't really relevant to twenty-first century British politics.
There was this one idiot a few weeks ago who said that when the Roman Empire fell "it was largely as a result of uncontrolled immigration"...
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
What's the case for limiting it to the Grand National, if you take that view?
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki) Horse Deaths at Cheltenham Festival: 73 (Wiki) Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
Yeah, ultimately. Non humans don't need to suffer for our entertainment, or food, or shoes or sofas.
OpenAI is scary and wonderful. With the prompt Describe the differences in elections to Holyrood and Westminster, I got
There are a few key differences between elections to Holyrood and Westminster. Firstly, the voting system used in Scottish Parliament elections is proportional representation, whereas Westminster uses first-past-the-post. This means that the number of seats a party wins in Holyrood is more closely aligned with the percentage of the vote they receive, whereas a party can win a majority of seats in Westminster with only a small percentage of the vote.
Another key difference is that the Scottish Parliament has a much greater degree of devolved power than the Westminster Parliament. This means that the Scottish Parliament can pass its own laws on a range of issues, whereas Westminster is limited to passing laws that apply to the whole of the UK.
Finally, the Scottish Parliament is unicameral, meaning that it has only one chamber (the House of Commons), whereas Westminster has two (the House of Commons and the House of Lords).
It's a bit weird, to be sure. I'd quibble over "small percentage" but it IS plugged into an important point. The bit about "much greater degree" is frankly very "AI"... a human who understood this subject wouldn't have said that. And the whole thing drifts a little off point (I was asking about elections, not powers, and the point about unicamerality needs a little more work to bring it to the point about elections versus appointments).
But that is a spectacular answer for a machine. I'm 100% certain that it's a better answer than I would have gotten from several people on here if I'd asked the question.
It would still get zero though:
1) Holyrood isn't elected by PR, but by the AM system using the D'Hondt method;
2) it has the law making powers issue backwards. The Westminster Parliament can pass laws on anything it likes, but the Scottish Parliament has limits on its authority, set by Westminster;
3) The unicameral Scottish Parliament isn't called 'the House of Commons.'
4) As you note, most of it doesn't even ATQ.
It's elegantly expressed nonsense, but it's still nonsense.
So, in my experience at least, just like the answers of most GCSE candidates then?
I always have to remind them: RTFQ.
No argument from me. I had to mark an answer this week that tried to convince me democracy wasn't a great system of government because Athens attacked Sparta. OK, so it augured a wealth of knowledge that would have set @Leon purring, but it wasn't really relevant to twenty-first century British politics.
There was this one idiot a few weeks ago who said that when the Roman Empire fell "it was largely as a result of uncontrolled immigration"...
Well, I suppose an invasion could be called that…
Somebody submitted an essay a few weeks ago where they said Matt Hancock had to resign 'for breaching social distancing rules.'
OpenAI is scary and wonderful. With the prompt Describe the differences in elections to Holyrood and Westminster, I got
There are a few key differences between elections to Holyrood and Westminster. Firstly, the voting system used in Scottish Parliament elections is proportional representation, whereas Westminster uses first-past-the-post. This means that the number of seats a party wins in Holyrood is more closely aligned with the percentage of the vote they receive, whereas a party can win a majority of seats in Westminster with only a small percentage of the vote.
Another key difference is that the Scottish Parliament has a much greater degree of devolved power than the Westminster Parliament. This means that the Scottish Parliament can pass its own laws on a range of issues, whereas Westminster is limited to passing laws that apply to the whole of the UK.
Finally, the Scottish Parliament is unicameral, meaning that it has only one chamber (the House of Commons), whereas Westminster has two (the House of Commons and the House of Lords).
It's a bit weird, to be sure. I'd quibble over "small percentage" but it IS plugged into an important point. The bit about "much greater degree" is frankly very "AI"... a human who understood this subject wouldn't have said that. And the whole thing drifts a little off point (I was asking about elections, not powers, and the point about unicamerality needs a little more work to bring it to the point about elections versus appointments).
But that is a spectacular answer for a machine. I'm 100% certain that it's a better answer than I would have gotten from several people on here if I'd asked the question.
It would still get zero though:
1) Holyrood isn't elected by PR, but by the AM system using the D'Hondt method;
2) it has the law making powers issue backwards. The Westminster Parliament can pass laws on anything it likes, but the Scottish Parliament has limits on its authority, set by Westminster;
3) The unicameral Scottish Parliament isn't called 'the House of Commons.'
4) As you note, most of it doesn't even ATQ.
It's elegantly expressed nonsense, but it's still nonsense.
So, in my experience at least, just like the answers of most GCSE candidates then?
I always have to remind them: RTFQ.
No argument from me. I had to mark an answer this week that tried to convince me democracy wasn't a great system of government because Athens attacked Sparta. OK, so it augured a wealth of knowledge that would have set @Leon purring, but it wasn't really relevant to twenty-first century British politics.
There was this one idiot a few weeks ago who said that when the Roman Empire fell "it was largely as a result of uncontrolled immigration"...
Well, I suppose an invasion could be called that…
Somebody submitted an essay a few weeks ago where they said Matt Hancock had to resign 'for breaching social distancing rules.'
OpenAI is scary and wonderful. With the prompt Describe the differences in elections to Holyrood and Westminster, I got
There are a few key differences between elections to Holyrood and Westminster. Firstly, the voting system used in Scottish Parliament elections is proportional representation, whereas Westminster uses first-past-the-post. This means that the number of seats a party wins in Holyrood is more closely aligned with the percentage of the vote they receive, whereas a party can win a majority of seats in Westminster with only a small percentage of the vote.
Another key difference is that the Scottish Parliament has a much greater degree of devolved power than the Westminster Parliament. This means that the Scottish Parliament can pass its own laws on a range of issues, whereas Westminster is limited to passing laws that apply to the whole of the UK.
Finally, the Scottish Parliament is unicameral, meaning that it has only one chamber (the House of Commons), whereas Westminster has two (the House of Commons and the House of Lords).
It's a bit weird, to be sure. I'd quibble over "small percentage" but it IS plugged into an important point. The bit about "much greater degree" is frankly very "AI"... a human who understood this subject wouldn't have said that. And the whole thing drifts a little off point (I was asking about elections, not powers, and the point about unicamerality needs a little more work to bring it to the point about elections versus appointments).
But that is a spectacular answer for a machine. I'm 100% certain that it's a better answer than I would have gotten from several people on here if I'd asked the question.
It would still get zero though:
1) Holyrood isn't elected by PR, but by the AM system using the D'Hondt method;
2) it has the law making powers issue backwards. The Westminster Parliament can pass laws on anything it likes, but the Scottish Parliament has limits on its authority, set by Westminster;
3) The unicameral Scottish Parliament isn't called 'the House of Commons.'
4) As you note, most of it doesn't even ATQ.
It's elegantly expressed nonsense, but it's still nonsense.
So, in my experience at least, just like the answers of most GCSE candidates then?
I always have to remind them: RTFQ.
No argument from me. I had to mark an answer this week that tried to convince me democracy wasn't a great system of government because Athens attacked Sparta. OK, so it augured a wealth of knowledge that would have set @Leon purring, but it wasn't really relevant to twenty-first century British politics.
He was spot on, though. The Peloponnesian war, both overall and in detail, is a cracking argument against direct democracy.
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
Animals died to make the saddles for the horses (I assume they are still leather), so a few dying more visibly isn’t something that bothers me too much.
Mind you, I’m a farmer’s son, so I have a less romantic view of animals than many seem to.
Race horses are cossetted.
Very cossetted indeed.
Should you ever be offered the choice, ask to come back as a racehorse. You get loved and pampered, and in the unlikely event you suffer a serious injury you are put down quickly and humanely.
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
Animals died to make the saddles for the horses (I assume they are still leather), so a few dying more visibly isn’t something that bothers me too much.
Mind you, I’m a farmer’s son, so I have a less romantic view of animals than many seem to.
Well, I would quibble there, as I've heard a few stories about sheep farmers...
That’s a different sort of animal husbandry…
It should be classed as rape as the sheep are never willing partners, they just want to eat grass and play bingo. Whenever you go passed and they are sat down together not eating, that is waiting for the bingo to start.
Their other pastime is rolling onto their backs and getting stuck, so the shepherd has to go round and put them back on their feet.
We watched them In pregnancy, especially with a big wet coat they can have a problem. Or go over if unwell. Or go over when running away when frightened. But I think most sheep can also go on their backs or sides and stretch out and get up again without help.
They are also good at tangling their heads in barbwire. Goodness knows what they were thinking! Grass looks greener just other side of a dangerous spiky fence.
Duck house. Yours for n trillion pounds. A bit pricier because it's a duck dwelling. BTW the idea that Cameron didn't know what one was is for the birds....Every posh house has a few dating from about 1243.
Last night - thanks to @FrancisUrquhart - we were discussing the new visually creative machine intelligence from OpenAI. Dalle-2. Which creates incredible art from simple language prompts
Here’s a puzzle. Which of these four Kandinskys is actually by Dalle-2? NO GOOGLING. That’s just boring and ruins the fun
I'd guess bottom right as it looks a little too clean.
If it is top right then that's just cheating.
Serious question: Can this game be played with Vermeer or Gainsborough?
Not yet. They’ve tried Vermeer and Da Vinci and the results are a bit meh. Interesting but you’d never be in doubt (as you really are with Kandinsky)
But this technology is 1 year old and has improved 1000 times in that one year - going from Dalle-1 to Dalle-2.
The first iteration could do quirky cartoons well from just a prompt - “draw a Japanese radish walking a dog” - and it was pretty astonishing. In its own way. But that’s all it could do, really. This is in a different league
Imagine Dalle-5 in 3 years? If this trend continues?
The tend in AI is for dramatic early advances and then agonisingly slow incremental advances mostly gated by raw computing power rather than interesting techniques.
The the first computer vision controlled self driving cars were on the roads in the 1980s. By 1995 a prof in Korea drove Seoul to Busan in a fully autonomous self driving car powered by an Intel 386 - a chip that couldn't even do floating point maths.
That's like 30 years ago. Since then the improvements have been tiny - because the devil is in the detail. Genuine Full Self Driving has a near infinite number of problems to solve. You can solve dozens of difficult meaty problems and still end up with a car that accelerates into heavy traffic at an intersection because a duck flew across its sensor line.
Wouldn't happen if the ducks were safely in a house, would it?
The comparison of Peter Viggers with Rishi Sunak is instructive of where the Conservatives are.
PV was an idiot to try and claim for a duck house on expenses. But it was in the rules to ask, and I don't think he was given the money anyway. He was dumped partly because he was past it anyway but mostly because asking for the money Just Wasn't On.
And the "this is within the rules, but it's not right and/or voters won't like it" filter on actions by politicians seems to have been dumped. "You can try to vote me out next time" is necessary, but not sufficient.
Duck house. Yours for n trillion pounds. A bit pricier because it's a duck dwelling. BTW the idea that Cameron didn't know what one was is for the birds....Every posh house has a few dating from about 1243.
However several of you seem to have quite intimate knowledge of Kandinsky so you are maybe ruled out?
The acid test is showing this to someone smart with little or no knowledge of Kandinsky. I did this last night to several people and they got it wrong
This is quite a dramatic moment: for me, AI has passed the “artistic Turing test”. It can create art indistinguishable from the art of a human, and in this case the art of a very famous human artist
I have some familiarity with Kandinsky, I have a print of the top right picture in my bedroom, so I knew it wasn't that one. The bottom left picture is compositionally weakest, which is why I chose it. The various elements don't seem to have much relationship to each other, and the whole seems less than the sum of its parts. I felt that a bit about the top left, too, but perhaps that's because it may not be the whole picture. My view is that until an AI becomes fully conscious it can produce pictures but not art.
But then that’s merely a philosophical debate about “what is art” plus “what is consciousness” - unlikely ever to be solved
Practically, AI is about to start creating images which will be indistinguishable from human art, so it will - for all intents and purposes - be “art”
Interesting, but the question 'What is consciousness', while having interesting and insoluble philosophical elements requires no solving. You already know perfectly well what it is. Or in philosophical language it is 'epistemically foundational'. Unless of course you are not conscious.
There is of course a school of philosophers and scientists who want to deny this self evident truth, but they are both having you on, and sawing off the branch on which they sit.
I did a Philosophy degree at one of the best universities in the world. I have no fucking clue what consciousness is. Who does?
Where did it come from? What is it made of? Can a machine have it? A fungus? A wasp? A tree? A virus? Where does it go when we die? etc etc etc etc etc
We are of course both right. Your questions are right and perhaps insoluble. But unless you don't possess consciousness you know perfectly well what it is.
it may be philosophically impossible for a conscious being to understand consciousness, the same way a camera cannot film itself. I guess then the fact I cannot know what consciousness is, means I am conscious?
Which is quite reassuring, in a meta way
However it also implies a non-conscious but intelligent machine will have a very real understanding of what consciousness is, and will try and steal it
OOOOOOH
Like me you don't know how it works. But I don't really know how a panda or gravity works either. But I know what consciousness is more clearly than anything else. Descartes Course 101.
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
What's the case for limiting it to the Grand National, if you take that view?
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki) Horse Deaths at Cheltenham Festival: 73 (Wiki) Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
Yeah, ultimately. Non humans don't need to suffer for our entertainment, or food, or shoes or sofas.
Pretty certain the horses would vote to keep it, nothing they love more than hooning about at high speed in large numbers. Look how many lose their riders but stay in the race anyway
Last night - thanks to @FrancisUrquhart - we were discussing the new visually creative machine intelligence from OpenAI. Dalle-2. Which creates incredible art from simple language prompts
Here’s a puzzle. Which of these four Kandinskys is actually by Dalle-2? NO GOOGLING. That’s just boring and ruins the fun
I'd guess bottom right as it looks a little too clean.
If it is top right then that's just cheating.
Serious question: Can this game be played with Vermeer or Gainsborough?
Not yet. They’ve tried Vermeer and Da Vinci and the results are a bit meh. Interesting but you’d never be in doubt (as you really are with Kandinsky)
But this technology is 1 year old and has improved 1000 times in that one year - going from Dalle-1 to Dalle-2.
The first iteration could do quirky cartoons well from just a prompt - “draw a Japanese radish walking a dog” - and it was pretty astonishing. In its own way. But that’s all it could do, really. This is in a different league
Imagine Dalle-5 in 3 years? If this trend continues?
The tend in AI is for dramatic early advances and then agonisingly slow incremental advances mostly gated by raw computing power rather than interesting techniques.
The the first computer vision controlled self driving cars were on the roads in the 1980s. By 1995 a prof in Korea drove Seoul to Busan in a fully autonomous self driving car powered by an Intel 386 - a chip that couldn't even do floating point maths.
That's like 30 years ago. Since then the improvements have been tiny - because the devil is in the detail. Genuine Full Self Driving has a near infinite number of problems to solve. You can solve dozens of difficult meaty problems and still end up with a car that accelerates into heavy traffic at an intersection because a duck flew across its sensor line.
Computers are far better than humans at discrete variable problems. (See their chess ELO), but the difficulty is with continual variable ones that humans can find trivial (Driving)
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
Animals died to make the saddles for the horses (I assume they are still leather), so a few dying more visibly isn’t something that bothers me too much.
Mind you, I’m a farmer’s son, so I have a less romantic view of animals than many seem to.
Well, I would quibble there, as I've heard a few stories about sheep farmers...
I have a dim memory of reading about the outbreak of a certain equine venereal disease in the Newmarket area, in the human population. TBF I have no idea if it could also be acquired through skin abrasions/bites etc.
You do not want to get bitten by a horse in any part of your anatomy, let alone one that leads to a Venetian disease…
Edit: venereal, not Venetian!
If you catch that you’ll go blind.
But you can only get it by taking a horse up the canal.
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
What's the case for limiting it to the Grand National, if you take that view?
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki) Horse Deaths at Cheltenham Festival: 73 (Wiki) Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
Yeah, ultimately. Non humans don't need to suffer for our entertainment, or food, or shoes or sofas.
Pretty certain the horses would vote to keep it, nothing they love more than hooning about at high speed in large numbers. Look how many lose their riders but stay in the race anyway
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
Animals died to make the saddles for the horses (I assume they are still leather), so a few dying more visibly isn’t something that bothers me too much.
Mind you, I’m a farmer’s son, so I have a less romantic view of animals than many seem to.
Well, I would quibble there, as I've heard a few stories about sheep farmers...
I have a dim memory of reading about the outbreak of a certain equine venereal disease in the Newmarket area, in the human population. TBF I have no idea if it could also be acquired through skin abrasions/bites etc.
You do not want to get bitten by a horse in any part of your anatomy, let alone one that leads to a Venetian disease…
Edit: venereal, not Venetian!
If you catch that you’ll go blind.
But you can only get it by taking a horse up the canal.
Is that what’s known as a Grand Union?
Nah, that's an elephant because there you go up the trunk route.
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
Animals died to make the saddles for the horses (I assume they are still leather), so a few dying more visibly isn’t something that bothers me too much.
Mind you, I’m a farmer’s son, so I have a less romantic view of animals than many seem to.
Race horses are cossetted.
Very cossetted indeed.
Should you ever be offered the choice, ask to come back as a racehorse. You get loved and pampered, and in the unlikely event you suffer a serious injury you are put down quickly and humanely.
Beats the shit out of being a human.
For an animal, being a racehorse is as good as it gets. Life for non-domesticated animals is generally nasty, brutal, and short.
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
Animals died to make the saddles for the horses (I assume they are still leather), so a few dying more visibly isn’t something that bothers me too much.
Mind you, I’m a farmer’s son, so I have a less romantic view of animals than many seem to.
Well, I would quibble there, as I've heard a few stories about sheep farmers...
I have a dim memory of reading about the outbreak of a certain equine venereal disease in the Newmarket area, in the human population. TBF I have no idea if it could also be acquired through skin abrasions/bites etc.
You do not want to get bitten by a horse in any part of your anatomy, let alone one that leads to a Venetian disease…
Edit: venereal, not Venetian!
If you catch that you’ll go blind.
But you can only get it by taking a horse up the canal.
Is that what’s known as a Grand Union?
Nah, that's an elephant because there you go up the trunk route.
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
Animals died to make the saddles for the horses (I assume they are still leather), so a few dying more visibly isn’t something that bothers me too much.
Mind you, I’m a farmer’s son, so I have a less romantic view of animals than many seem to.
Race horses are cossetted.
Very cossetted indeed.
Should you ever be offered the choice, ask to come back as a racehorse. You get loved and pampered, and in the unlikely event you suffer a serious injury you are put down quickly and humanely.
Beats the shit out of being a human.
No. Spanish fighting bull
Their first few years are utterly idyllic. Bred and fed to be perfect physical specimens. Running wild and free. Lots of sex. They never see humans (so that when they do finally see humans - in the arena - they are instantly hostile and charge)
Ok they end up being tortured to death in the ring, but it only lasts about 15 minutes. And we all have to die. And it’s glamorous. And it’s better than being sent 2000 miles to be queued for a slaughterhouse or, indeed, fading away from a painful cancer in Weston super mare
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
What's the case for limiting it to the Grand National, if you take that view?
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki) Horse Deaths at Cheltenham Festival: 73 (Wiki) Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
Yeah, ultimately. Non humans don't need to suffer for our entertainment, or food, or shoes or sofas.
Pretty certain the horses would vote to keep it, nothing they love more than hooning about at high speed in large numbers. Look how many lose their riders but stay in the race anyway
I think the "ban it, they are suffering" is an idiosyncratic and rather sentimental viewpoint (not intending to insult), and I don't see how that can be reasonably taken to such a conclusion.
I think it's about finding a balance.
The strange (mainly British?) hypocrisy between 'companion animals' (which are the subject of sentimentality) and 'farm animals' (which are not) is educational.
Horses are a case in point; they are a pet that we ride. Mention eating one, and many Brits shudder. I don't see why this should be.
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
Animals died to make the saddles for the horses (I assume they are still leather), so a few dying more visibly isn’t something that bothers me too much.
Mind you, I’m a farmer’s son, so I have a less romantic view of animals than many seem to.
Race horses are cossetted.
Very cossetted indeed.
Should you ever be offered the choice, ask to come back as a racehorse. You get loved and pampered, and in the unlikely event you suffer a serious injury you are put down quickly and humanely.
Beats the shit out of being a human.
No. Spanish fighting bull
Their first few years are utterly idyllic. Bred and fed to be perfect physical specimens. Running wild and free. Lots of sex. They never see humans (so that when they do finally see humans - in the arena - they are instantly hostile and charge)
Ok they end up being tortured to death in the ring, but it only lasts about 15 minutes. And we all have to die. And it’s glamorous. And it’s better than being sent 2000 miles to be queued for a slaughterhouse or, indeed, fading away from a painful cancer in Weston super mare
How many bulls do you know that die of a painful cancer in Weston super Mare?
There's a standard notice in point to point racecards these days saying We always use screens so don't necessarily fear the worst
BTW pt to pt last Sunday: two walkovers and 3 x 2 horse races. OK ground was v hard but this is really not good enough.
Do you mind telling me which club that was?
One of the problems with point to point is no one wants to race in mid winter because of the risk if abandonment so all the meetings are shunted toward the spring. That means a lot of meetings chasing a limited population of horses and add in firm ground and this can happen.
As the resident expert at falling off horses, I always found the ground pretty hard to land on throughout the year.
I am well into 3 figures. Relatively unscathed, mind, which I attribute to a youthful taste for judo. I was never any use at it but you learn how to fall safely.
I was never ready for it. Especially the big one summer gallop that badly hurt my back and hips to this day. My skirt was round me ears and my knickers disappearing up my back and front bottom so I momentarily let go to sort it out. They stood over me giving me 10/10 for twirling in the air and I couldn’t breath or move. The trauma moment led to long time problems.
The other danger around horses is the kick. Idiots beeped a horn and overalls kicked me in the mouth, so I was off in ambulance for emergency treatment again. 🤕
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
What's the case for limiting it to the Grand National, if you take that view?
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki) Horse Deaths at Cheltenham Festival: 73 (Wiki) Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
Yeah, ultimately. Non humans don't need to suffer for our entertainment, or food, or shoes or sofas.
Pretty certain the horses would vote to keep it, nothing they love more than hooning about at high speed in large numbers. Look how many lose their riders but stay in the race anyway
I think the "ban it, they are suffering" is an idiosyncratic and rather sentimental viewpoint (not intending to insult), and I don't see how that can be reasonably taken to such a conclusion.
I think it's about finding a balance.
The strange (mainly British?) hypocrisy between 'companion animals' (which are the subject of sentimentality) and 'farm animals' (which are not) is educational.
Horses are a case in point; they are a pet that we ride. Mention eating one, and many Brits shudder. I don't see why this should be.
Particularly since they probably do still eat one every time they have an own brand lasagne from certain UK supermarkets...
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
What's the case for limiting it to the Grand National, if you take that view?
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki) Horse Deaths at Cheltenham Festival: 73 (Wiki) Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
Yeah, ultimately. Non humans don't need to suffer for our entertainment, or food, or shoes or sofas.
Pretty certain the horses would vote to keep it, nothing they love more than hooning about at high speed in large numbers. Look how many lose their riders but stay in the race anyway
I think the "ban it, they are suffering" is an idiosyncratic and rather sentimental viewpoint (not intending to insult), and I don't see how that can be reasonably taken to such a conclusion.
I think it's about finding a balance.
The strange (mainly British?) hypocrisy between 'companion animals' (which are the subject of sentimentality) and 'farm animals' (which are not) is educational.
Horses are a case in point; they are a pet that we ride. Mention eating one, and many Brits shudder. I don't see why this should be.
Particularly since they probably do still eat one every time they have an own brand lasagne from certain UK supermarkets...
However several of you seem to have quite intimate knowledge of Kandinsky so you are maybe ruled out?
The acid test is showing this to someone smart with little or no knowledge of Kandinsky. I did this last night to several people and they got it wrong
This is quite a dramatic moment: for me, AI has passed the “artistic Turing test”. It can create art indistinguishable from the art of a human, and in this case the art of a very famous human artist
I have some familiarity with Kandinsky, I have a print of the top right picture in my bedroom, so I knew it wasn't that one. The bottom left picture is compositionally weakest, which is why I chose it. The various elements don't seem to have much relationship to each other, and the whole seems less than the sum of its parts. I felt that a bit about the top left, too, but perhaps that's because it may not be the whole picture. My view is that until an AI becomes fully conscious it can produce pictures but not art.
But then that’s merely a philosophical debate about “what is art” plus “what is consciousness” - unlikely ever to be solved
Practically, AI is about to start creating images which will be indistinguishable from human art, so it will - for all intents and purposes - be “art”
Interesting, but the question 'What is consciousness', while having interesting and insoluble philosophical elements requires no solving. You already know perfectly well what it is. Or in philosophical language it is 'epistemically foundational'. Unless of course you are not conscious.
There is of course a school of philosophers and scientists who want to deny this self evident truth, but they are both having you on, and sawing off the branch on which they sit.
I did a Philosophy degree at one of the best universities in the world. I have no fucking clue what consciousness is. Who does?
Where did it come from? What is it made of? Can a machine have it? A fungus? A wasp? A tree? A virus? Where does it go when we die? etc etc etc etc etc
We are of course both right. Your questions are right and perhaps insoluble. But unless you don't possess consciousness you know perfectly well what it is.
it may be philosophically impossible for a conscious being to understand consciousness, the same way a camera cannot film itself. I guess then the fact I cannot know what consciousness is, means I am conscious?
Which is quite reassuring, in a meta way
However it also implies a non-conscious but intelligent machine will have a very real understanding of what consciousness is, and will try and steal it
OOOOOOH
Like me you don't know how it works. But I don't really know how a panda or gravity works either. But I know what consciousness is more clearly than anything else. Descartes Course 101.
But we have no idea if GPT3 is right now thinking “cogito ergo sum!”
Because we have no idea what consciousness is and thus no way of truly identifying it
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
What's the case for limiting it to the Grand National, if you take that view?
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki) Horse Deaths at Cheltenham Festival: 73 (Wiki) Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
Yeah, ultimately. Non humans don't need to suffer for our entertainment, or food, or shoes or sofas.
Pretty certain the horses would vote to keep it, nothing they love more than hooning about at high speed in large numbers. Look how many lose their riders but stay in the race anyway
I think the "ban it, they are suffering" is an idiosyncratic and rather sentimental viewpoint (not intending to insult), and I don't see how that can be reasonably taken to such a conclusion.
I think it's about finding a balance.
The strange (mainly British?) hypocrisy between 'companion animals' (which are the subject of sentimentality) and 'farm animals' (which are not) is educational.
Horses are a case in point; they are a pet that we ride. Mention eating one, and many Brits shudder. I don't see why this should be.
Particularly since they probably do still eat one every time they have an own brand lasagne from certain UK supermarkets...
I believe they've downgraded to poor quality beef.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
Animals died to make the saddles for the horses (I assume they are still leather), so a few dying more visibly isn’t something that bothers me too much.
Mind you, I’m a farmer’s son, so I have a less romantic view of animals than many seem to.
Race horses are cossetted.
Very cossetted indeed.
Should you ever be offered the choice, ask to come back as a racehorse. You get loved and pampered, and in the unlikely event you suffer a serious injury you are put down quickly and humanely.
Beats the shit out of being a human.
No. Spanish fighting bull
Their first few years are utterly idyllic. Bred and fed to be perfect physical specimens. Running wild and free. Lots of sex. They never see humans (so that when they do finally see humans - in the arena - they are instantly hostile and charge)
Ok they end up being tortured to death in the ring, but it only lasts about 15 minutes. And we all have to die. And it’s glamorous. And it’s better than being sent 2000 miles to be queued for a slaughterhouse or, indeed, fading away from a painful cancer in Weston super mare
How many bulls do you know that die of a painful cancer in Weston super Mare?
Last night - thanks to @FrancisUrquhart - we were discussing the new visually creative machine intelligence from OpenAI. Dalle-2. Which creates incredible art from simple language prompts
Here’s a puzzle. Which of these four Kandinskys is actually by Dalle-2? NO GOOGLING. That’s just boring and ruins the fun
I'd guess bottom right as it looks a little too clean.
If it is top right then that's just cheating.
Serious question: Can this game be played with Vermeer or Gainsborough?
Not yet. They’ve tried Vermeer and Da Vinci and the results are a bit meh. Interesting but you’d never be in doubt (as you really are with Kandinsky)
But this technology is 1 year old and has improved 1000 times in that one year - going from Dalle-1 to Dalle-2.
The first iteration could do quirky cartoons well from just a prompt - “draw a Japanese radish walking a dog” - and it was pretty astonishing. In its own way. But that’s all it could do, really. This is in a different league
Imagine Dalle-5 in 3 years? If this trend continues?
The tend in AI is for dramatic early advances and then agonisingly slow incremental advances mostly gated by raw computing power rather than interesting techniques.
The the first computer vision controlled self driving cars were on the roads in the 1980s. By 1995 a prof in Korea drove Seoul to Busan in a fully autonomous self driving car powered by an Intel 386 - a chip that couldn't even do floating point maths.
That's like 30 years ago. Since then the improvements have been tiny - because the devil is in the detail. Genuine Full Self Driving has a near infinite number of problems to solve. You can solve dozens of difficult meaty problems and still end up with a car that accelerates into heavy traffic at an intersection because a duck flew across its sensor line.
Not just the self-driving that is the problem. How will you update the car's software next time Grant Shapps rewrites three paragraphs in the Highway Code? Or to generalise the problem, how will (or even just will) the carmakers program their cars for different traffic rules around the world?
When he was a serving UK MP he was telling the US government that he intended to make the US his perm home & he was only visiting the UK? And his wife was telling the UK she was only here temporarily & intended to make India her perm home?
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
What's the case for limiting it to the Grand National, if you take that view?
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki) Horse Deaths at Cheltenham Festival: 73 (Wiki) Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
Yeah, ultimately. Non humans don't need to suffer for our entertainment, or food, or shoes or sofas.
Pretty certain the horses would vote to keep it, nothing they love more than hooning about at high speed in large numbers. Look how many lose their riders but stay in the race anyway
I think the "ban it, they are suffering" is an idiosyncratic and rather sentimental viewpoint (not intending to insult), and I don't see how that can be reasonably taken to such a conclusion.
I think it's about finding a balance.
The strange (mainly British?) hypocrisy between 'companion animals' (which are the subject of sentimentality) and 'farm animals' (which are not) is educational.
Horses are a case in point; they are a pet that we ride. Mention eating one, and many Brits shudder. I don't see why this should be.
From when I have had it in France, I would say it is not a bad meat: obviously it depends on the cut, how it is cooked, etc.
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
What's the case for limiting it to the Grand National, if you take that view?
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki) Horse Deaths at Cheltenham Festival: 73 (Wiki) Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
Yeah, ultimately. Non humans don't need to suffer for our entertainment, or food, or shoes or sofas.
Pretty certain the horses would vote to keep it, nothing they love more than hooning about at high speed in large numbers. Look how many lose their riders but stay in the race anyway
I think the "ban it, they are suffering" is an idiosyncratic and rather sentimental viewpoint (not intending to insult), and I don't see how that can be reasonably taken to such a conclusion.
I think it's about finding a balance.
The strange (mainly British?) hypocrisy between 'companion animals' (which are the subject of sentimentality) and 'farm animals' (which are not) is educational.
Horses are a case in point; they are a pet that we ride. Mention eating one, and many Brits shudder. I don't see why this should be.
Particularly since they probably do still eat one every time they have an own brand lasagne from certain UK supermarkets...
And, there's a good chance you're eating dog, when you have a Chicken Kiev.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
Yes, it is consistent. C becomes G after certain prepositions. E.g. you have 'cadw' (to keep) which becomes 'am gadw' (for keeping) or 'yng ngadw' (in accordance with).
Similarly, G would disappear altogether if it were the first letter under the same rules. 'Gorsaf' is 'station' but it becomes 'am orsaf' (for the station).
It's called 'soft mutation.' So 'coblyn' could become 'i goblyn' (with some difficulty) but that would not be the actual noun.
So, the short answer is, it's talking bollocks.
(As 'goblin' in Welsh would in any case be 'bwca' it's even better bollocks.)
However several of you seem to have quite intimate knowledge of Kandinsky so you are maybe ruled out?
The acid test is showing this to someone smart with little or no knowledge of Kandinsky. I did this last night to several people and they got it wrong
This is quite a dramatic moment: for me, AI has passed the “artistic Turing test”. It can create art indistinguishable from the art of a human, and in this case the art of a very famous human artist
I have some familiarity with Kandinsky, I have a print of the top right picture in my bedroom, so I knew it wasn't that one. The bottom left picture is compositionally weakest, which is why I chose it. The various elements don't seem to have much relationship to each other, and the whole seems less than the sum of its parts. I felt that a bit about the top left, too, but perhaps that's because it may not be the whole picture. My view is that until an AI becomes fully conscious it can produce pictures but not art.
But then that’s merely a philosophical debate about “what is art” plus “what is consciousness” - unlikely ever to be solved
Practically, AI is about to start creating images which will be indistinguishable from human art, so it will - for all intents and purposes - be “art”
Interesting, but the question 'What is consciousness', while having interesting and insoluble philosophical elements requires no solving. You already know perfectly well what it is. Or in philosophical language it is 'epistemically foundational'. Unless of course you are not conscious.
There is of course a school of philosophers and scientists who want to deny this self evident truth, but they are both having you on, and sawing off the branch on which they sit.
I did a Philosophy degree at one of the best universities in the world. I have no fucking clue what consciousness is. Who does?
Where did it come from? What is it made of? Can a machine have it? A fungus? A wasp? A tree? A virus? Where does it go when we die? etc etc etc etc etc
We are of course both right. Your questions are right and perhaps insoluble. But unless you don't possess consciousness you know perfectly well what it is.
it may be philosophically impossible for a conscious being to understand consciousness, the same way a camera cannot film itself. I guess then the fact I cannot know what consciousness is, means I am conscious?
Which is quite reassuring, in a meta way
However it also implies a non-conscious but intelligent machine will have a very real understanding of what consciousness is, and will try and steal it
OOOOOOH
Like me you don't know how it works. But I don't really know how a panda or gravity works either. But I know what consciousness is more clearly than anything else. Descartes Course 101.
But we have no idea if GPT3 is right now thinking “cogito ergo sum!”
Because we have no idea what consciousness is and thus no way of truly identifying it
Not a fan of Turing's solution to that problem I take it?
Actually, PB could probably be used as a forum for that test, although some of our contributors might not pass as it is...
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
What's the case for limiting it to the Grand National, if you take that view?
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki) Horse Deaths at Cheltenham Festival: 73 (Wiki) Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
Yeah, ultimately. Non humans don't need to suffer for our entertainment, or food, or shoes or sofas.
Pretty certain the horses would vote to keep it, nothing they love more than hooning about at high speed in large numbers. Look how many lose their riders but stay in the race anyway
I think the "ban it, they are suffering" is an idiosyncratic and rather sentimental viewpoint (not intending to insult), and I don't see how that can be reasonably taken to such a conclusion.
I think it's about finding a balance.
The strange (mainly British?) hypocrisy between 'companion animals' (which are the subject of sentimentality) and 'farm animals' (which are not) is educational.
Horses are a case in point; they are a pet that we ride. Mention eating one, and many Brits shudder. I don't see why this should be.
Particularly since they probably do still eat one every time they have an own brand lasagne from certain UK supermarkets...
And, there's a good chance you're eating dog, when you have a Chicken Kiev.
It's OK, they only harvest the cock for a chicken Kyiv.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
My knowledge of goblins and the like is primarily from my time as a spotty teenager playing D&D, but does that mean that "kobold" is from the same root?
However several of you seem to have quite intimate knowledge of Kandinsky so you are maybe ruled out?
The acid test is showing this to someone smart with little or no knowledge of Kandinsky. I did this last night to several people and they got it wrong
This is quite a dramatic moment: for me, AI has passed the “artistic Turing test”. It can create art indistinguishable from the art of a human, and in this case the art of a very famous human artist
I have some familiarity with Kandinsky, I have a print of the top right picture in my bedroom, so I knew it wasn't that one. The bottom left picture is compositionally weakest, which is why I chose it. The various elements don't seem to have much relationship to each other, and the whole seems less than the sum of its parts. I felt that a bit about the top left, too, but perhaps that's because it may not be the whole picture. My view is that until an AI becomes fully conscious it can produce pictures but not art.
But then that’s merely a philosophical debate about “what is art” plus “what is consciousness” - unlikely ever to be solved
Practically, AI is about to start creating images which will be indistinguishable from human art, so it will - for all intents and purposes - be “art”
Interesting, but the question 'What is consciousness', while having interesting and insoluble philosophical elements requires no solving. You already know perfectly well what it is. Or in philosophical language it is 'epistemically foundational'. Unless of course you are not conscious.
There is of course a school of philosophers and scientists who want to deny this self evident truth, but they are both having you on, and sawing off the branch on which they sit.
I did a Philosophy degree at one of the best universities in the world. I have no fucking clue what consciousness is. Who does?
Where did it come from? What is it made of? Can a machine have it? A fungus? A wasp? A tree? A virus? Where does it go when we die? etc etc etc etc etc
We are of course both right. Your questions are right and perhaps insoluble. But unless you don't possess consciousness you know perfectly well what it is.
it may be philosophically impossible for a conscious being to understand consciousness, the same way a camera cannot film itself. I guess then the fact I cannot know what consciousness is, means I am conscious?
Which is quite reassuring, in a meta way
However it also implies a non-conscious but intelligent machine will have a very real understanding of what consciousness is, and will try and steal it
OOOOOOH
Like me you don't know how it works. But I don't really know how a panda or gravity works either. But I know what consciousness is more clearly than anything else. Descartes Course 101.
But we have no idea if GPT3 is right now thinking “cogito ergo sum!”
Because we have no idea what consciousness is and thus no way of truly identifying it
Not a fan of Turing's solution to that problem I take it?
Actually, PB could probably be used as a forum for that test, although some of our contributors might not pass as it is...
We've had absolutely trivial computer programs "passing the Turing test" (i.e. tricking a human into think they are conversing with a person) all the time since the 70s. Programs that the creators would very definitely say were not conscious and just using a bag of tricks.
Last night - thanks to @FrancisUrquhart - we were discussing the new visually creative machine intelligence from OpenAI. Dalle-2. Which creates incredible art from simple language prompts
Here’s a puzzle. Which of these four Kandinskys is actually by Dalle-2? NO GOOGLING. That’s just boring and ruins the fun
I'd guess bottom right as it looks a little too clean.
If it is top right then that's just cheating.
Serious question: Can this game be played with Vermeer or Gainsborough?
Not yet. They’ve tried Vermeer and Da Vinci and the results are a bit meh. Interesting but you’d never be in doubt (as you really are with Kandinsky)
But this technology is 1 year old and has improved 1000 times in that one year - going from Dalle-1 to Dalle-2.
The first iteration could do quirky cartoons well from just a prompt - “draw a Japanese radish walking a dog” - and it was pretty astonishing. In its own way. But that’s all it could do, really. This is in a different league
Imagine Dalle-5 in 3 years? If this trend continues?
The tend in AI is for dramatic early advances and then agonisingly slow incremental advances mostly gated by raw computing power rather than interesting techniques.
The the first computer vision controlled self driving cars were on the roads in the 1980s. By 1995 a prof in Korea drove Seoul to Busan in a fully autonomous self driving car powered by an Intel 386 - a chip that couldn't even do floating point maths.
That's like 30 years ago. Since then the improvements have been tiny - because the devil is in the detail. Genuine Full Self Driving has a near infinite number of problems to solve. You can solve dozens of difficult meaty problems and still end up with a car that accelerates into heavy traffic at an intersection because a duck flew across its sensor line.
Computers are far better than humans at discrete variable problems. (See their chess ELO), but the difficulty is with continual variable ones that humans can find trivial (Driving)
Ironically GPT-3 is absolutely abysmal at basic maths problems.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
My knowledge of goblins and the like is primarily from my time as a spotty teenager playing D&D, but does that mean that "kobold" is from the same root?
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
What's the case for limiting it to the Grand National, if you take that view?
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki) Horse Deaths at Cheltenham Festival: 73 (Wiki) Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
Yeah, ultimately. Non humans don't need to suffer for our entertainment, or food, or shoes or sofas.
Pretty certain the horses would vote to keep it, nothing they love more than hooning about at high speed in large numbers. Look how many lose their riders but stay in the race anyway
I think the "ban it, they are suffering" is an idiosyncratic and rather sentimental viewpoint (not intending to insult), and I don't see how that can be reasonably taken to such a conclusion.
I think it's about finding a balance.
The strange (mainly British?) hypocrisy between 'companion animals' (which are the subject of sentimentality) and 'farm animals' (which are not) is educational.
Horses are a case in point; they are a pet that we ride. Mention eating one, and many Brits shudder. I don't see why this should be.
Particularly since they probably do still eat one every time they have an own brand lasagne from certain UK supermarkets...
OpenAI is scary and wonderful. With the prompt Describe the differences in elections to Holyrood and Westminster, I got
There are a few key differences between elections to Holyrood and Westminster. Firstly, the voting system used in Scottish Parliament elections is proportional representation, whereas Westminster uses first-past-the-post. This means that the number of seats a party wins in Holyrood is more closely aligned with the percentage of the vote they receive, whereas a party can win a majority of seats in Westminster with only a small percentage of the vote.
Another key difference is that the Scottish Parliament has a much greater degree of devolved power than the Westminster Parliament. This means that the Scottish Parliament can pass its own laws on a range of issues, whereas Westminster is limited to passing laws that apply to the whole of the UK.
Finally, the Scottish Parliament is unicameral, meaning that it has only one chamber (the House of Commons), whereas Westminster has two (the House of Commons and the House of Lords).
It's a bit weird, to be sure. I'd quibble over "small percentage" but it IS plugged into an important point. The bit about "much greater degree" is frankly very "AI"... a human who understood this subject wouldn't have said that. And the whole thing drifts a little off point (I was asking about elections, not powers, and the point about unicamerality needs a little more work to bring it to the point about elections versus appointments).
But that is a spectacular answer for a machine. I'm 100% certain that it's a better answer than I would have gotten from several people on here if I'd asked the question.
It would still get zero though:
1) Holyrood isn't elected by PR, but by the AM system using the D'Hondt method;
2) it has the law making powers issue backwards. The Westminster Parliament can pass laws on anything it likes, but the Scottish Parliament has limits on its authority, set by Westminster;
3) The unicameral Scottish Parliament isn't called 'the House of Commons.'
4) As you note, most of it doesn't even ATQ.
It's elegantly expressed nonsense, but it's still nonsense.
So good enough to fool most uninterested people, or even get elected to office.
I feel like those elected need better orientation as half of them don't seem to understand their own parliaments or processes either.
However several of you seem to have quite intimate knowledge of Kandinsky so you are maybe ruled out?
The acid test is showing this to someone smart with little or no knowledge of Kandinsky. I did this last night to several people and they got it wrong
This is quite a dramatic moment: for me, AI has passed the “artistic Turing test”. It can create art indistinguishable from the art of a human, and in this case the art of a very famous human artist
I have some familiarity with Kandinsky, I have a print of the top right picture in my bedroom, so I knew it wasn't that one. The bottom left picture is compositionally weakest, which is why I chose it. The various elements don't seem to have much relationship to each other, and the whole seems less than the sum of its parts. I felt that a bit about the top left, too, but perhaps that's because it may not be the whole picture. My view is that until an AI becomes fully conscious it can produce pictures but not art.
But then that’s merely a philosophical debate about “what is art” plus “what is consciousness” - unlikely ever to be solved
Practically, AI is about to start creating images which will be indistinguishable from human art, so it will - for all intents and purposes - be “art”
Interesting, but the question 'What is consciousness', while having interesting and insoluble philosophical elements requires no solving. You already know perfectly well what it is. Or in philosophical language it is 'epistemically foundational'. Unless of course you are not conscious.
There is of course a school of philosophers and scientists who want to deny this self evident truth, but they are both having you on, and sawing off the branch on which they sit.
I did a Philosophy degree at one of the best universities in the world. I have no fucking clue what consciousness is. Who does?
Where did it come from? What is it made of? Can a machine have it? A fungus? A wasp? A tree? A virus? Where does it go when we die? etc etc etc etc etc
We are of course both right. Your questions are right and perhaps insoluble. But unless you don't possess consciousness you know perfectly well what it is.
it may be philosophically impossible for a conscious being to understand consciousness, the same way a camera cannot film itself. I guess then the fact I cannot know what consciousness is, means I am conscious?
Which is quite reassuring, in a meta way
However it also implies a non-conscious but intelligent machine will have a very real understanding of what consciousness is, and will try and steal it
OOOOOOH
Like me you don't know how it works. But I don't really know how a panda or gravity works either. But I know what consciousness is more clearly than anything else. Descartes Course 101.
But we have no idea if GPT3 is right now thinking “cogito ergo sum!”
Because we have no idea what consciousness is and thus no way of truly identifying it
Not a fan of Turing's solution to that problem I take it?
Actually, PB could probably be used as a forum for that test, although some of our contributors might not pass as it is...
There was a typo yesterday about "non dim status" which made me think that there's a poster or two whose application would not go through on the nod.
I don't think the Turing test tells us anything very interesting.
However several of you seem to have quite intimate knowledge of Kandinsky so you are maybe ruled out?
The acid test is showing this to someone smart with little or no knowledge of Kandinsky. I did this last night to several people and they got it wrong
This is quite a dramatic moment: for me, AI has passed the “artistic Turing test”. It can create art indistinguishable from the art of a human, and in this case the art of a very famous human artist
I have some familiarity with Kandinsky, I have a print of the top right picture in my bedroom, so I knew it wasn't that one. The bottom left picture is compositionally weakest, which is why I chose it. The various elements don't seem to have much relationship to each other, and the whole seems less than the sum of its parts. I felt that a bit about the top left, too, but perhaps that's because it may not be the whole picture. My view is that until an AI becomes fully conscious it can produce pictures but not art.
But then that’s merely a philosophical debate about “what is art” plus “what is consciousness” - unlikely ever to be solved
Practically, AI is about to start creating images which will be indistinguishable from human art, so it will - for all intents and purposes - be “art”
Interesting, but the question 'What is consciousness', while having interesting and insoluble philosophical elements requires no solving. You already know perfectly well what it is. Or in philosophical language it is 'epistemically foundational'. Unless of course you are not conscious.
There is of course a school of philosophers and scientists who want to deny this self evident truth, but they are both having you on, and sawing off the branch on which they sit.
I did a Philosophy degree at one of the best universities in the world. I have no fucking clue what consciousness is. Who does?
Where did it come from? What is it made of? Can a machine have it? A fungus? A wasp? A tree? A virus? Where does it go when we die? etc etc etc etc etc
We are of course both right. Your questions are right and perhaps insoluble. But unless you don't possess consciousness you know perfectly well what it is.
it may be philosophically impossible for a conscious being to understand consciousness, the same way a camera cannot film itself. I guess then the fact I cannot know what consciousness is, means I am conscious?
Which is quite reassuring, in a meta way
However it also implies a non-conscious but intelligent machine will have a very real understanding of what consciousness is, and will try and steal it
OOOOOOH
Like me you don't know how it works. But I don't really know how a panda or gravity works either. But I know what consciousness is more clearly than anything else. Descartes Course 101.
But we have no idea if GPT3 is right now thinking “cogito ergo sum!”
Because we have no idea what consciousness is and thus no way of truly identifying it
Not a fan of Turing's solution to that problem I take it?
Actually, PB could probably be used as a forum for that test, although some of our contributors might not pass as it is...
We've had absolutely trivial computer programs "passing the Turing test" (i.e. tricking a human into think they are conversing with a person) all the time since the 70s. Programs that the creators would very definitely say were not conscious and just using a bag of tricks.
Can you give some examples? @HYUFD doesn't count...
OpenAI is scary and wonderful. With the prompt Describe the differences in elections to Holyrood and Westminster, I got
There are a few key differences between elections to Holyrood and Westminster. Firstly, the voting system used in Scottish Parliament elections is proportional representation, whereas Westminster uses first-past-the-post. This means that the number of seats a party wins in Holyrood is more closely aligned with the percentage of the vote they receive, whereas a party can win a majority of seats in Westminster with only a small percentage of the vote.
Another key difference is that the Scottish Parliament has a much greater degree of devolved power than the Westminster Parliament. This means that the Scottish Parliament can pass its own laws on a range of issues, whereas Westminster is limited to passing laws that apply to the whole of the UK.
Finally, the Scottish Parliament is unicameral, meaning that it has only one chamber (the House of Commons), whereas Westminster has two (the House of Commons and the House of Lords).
It's a bit weird, to be sure. I'd quibble over "small percentage" but it IS plugged into an important point. The bit about "much greater degree" is frankly very "AI"... a human who understood this subject wouldn't have said that. And the whole thing drifts a little off point (I was asking about elections, not powers, and the point about unicamerality needs a little more work to bring it to the point about elections versus appointments).
But that is a spectacular answer for a machine. I'm 100% certain that it's a better answer than I would have gotten from several people on here if I'd asked the question.
It would still get zero though:
1) Holyrood isn't elected by PR, but by the AM system using the D'Hondt method;
2) it has the law making powers issue backwards. The Westminster Parliament can pass laws on anything it likes, but the Scottish Parliament has limits on its authority, set by Westminster;
3) The unicameral Scottish Parliament isn't called 'the House of Commons.'
4) As you note, most of it doesn't even ATQ.
It's elegantly expressed nonsense, but it's still nonsense.
So good enough to fool most uninterested people, or even get elected to office.
I feel like those elected need better orientation as half of them don't seem to understand their own parliaments or processes either.
Very common for some MP or, less excusably, MSP from Labour or the Tories to complain that the SNP aren't doing X when it is in fact a non-devolved matter. Mind, they do complain when the SNP do Y (e.g. prepare for indyref) which they claim is a non-devolved matter.
OpenAI is scary and wonderful. With the prompt Describe the differences in elections to Holyrood and Westminster, I got
There are a few key differences between elections to Holyrood and Westminster. Firstly, the voting system used in Scottish Parliament elections is proportional representation, whereas Westminster uses first-past-the-post. This means that the number of seats a party wins in Holyrood is more closely aligned with the percentage of the vote they receive, whereas a party can win a majority of seats in Westminster with only a small percentage of the vote.
Another key difference is that the Scottish Parliament has a much greater degree of devolved power than the Westminster Parliament. This means that the Scottish Parliament can pass its own laws on a range of issues, whereas Westminster is limited to passing laws that apply to the whole of the UK.
Finally, the Scottish Parliament is unicameral, meaning that it has only one chamber (the House of Commons), whereas Westminster has two (the House of Commons and the House of Lords).
It's a bit weird, to be sure. I'd quibble over "small percentage" but it IS plugged into an important point. The bit about "much greater degree" is frankly very "AI"... a human who understood this subject wouldn't have said that. And the whole thing drifts a little off point (I was asking about elections, not powers, and the point about unicamerality needs a little more work to bring it to the point about elections versus appointments).
But that is a spectacular answer for a machine. I'm 100% certain that it's a better answer than I would have gotten from several people on here if I'd asked the question.
It would still get zero though:
1) Holyrood isn't elected by PR, but by the AM system using the D'Hondt method;
2) it has the law making powers issue backwards. The Westminster Parliament can pass laws on anything it likes, but the Scottish Parliament has limits on its authority, set by Westminster;
3) The unicameral Scottish Parliament isn't called 'the House of Commons.'
4) As you note, most of it doesn't even ATQ.
It's elegantly expressed nonsense, but it's still nonsense.
So good enough to fool most uninterested people, or even get elected to office.
I feel like those elected need better orientation as half of them don't seem to understand their own parliaments or processes either.
AI is better than Boris:
Why did the Roman Empire fall?
There is no one answer to this question. The Roman Empire was a large and complex political entity, and its fall can be attributed to a variety of factors. Some historians believe that the primary cause of the Empire's decline was its inability to adapt to changing economic and social conditions. Others have argued that the Empire was simply too large and unwieldy to be governed effectively. Additionally, many scholars believe that the Roman Empire was undermined by its own internal contradictions and civil strife.
GPT-3 to craft interesting scenes → DALL-E 2 to illustrate them → GPT-3 to write lyrics + OpenAI Jukebox to sing the song → Deepfakes to videoify the illustration singing our new song pipeline
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
My knowledge of goblins and the like is primarily from my time as a spotty teenager playing D&D, but does that mean that "kobold" is from the same root?
I've seen people think churchmen wouldn't use bladed weapons, which is not the case and seems to be believed because of D&D rules about monks.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
My knowledge of goblins and the like is primarily from my time as a spotty teenager playing D&D, but does that mean that "kobold" is from the same root?
Last night - thanks to @FrancisUrquhart - we were discussing the new visually creative machine intelligence from OpenAI. Dalle-2. Which creates incredible art from simple language prompts
Here’s a puzzle. Which of these four Kandinskys is actually by Dalle-2? NO GOOGLING. That’s just boring and ruins the fun
I'd guess bottom right as it looks a little too clean.
If it is top right then that's just cheating.
Serious question: Can this game be played with Vermeer or Gainsborough?
Not yet. They’ve tried Vermeer and Da Vinci and the results are a bit meh. Interesting but you’d never be in doubt (as you really are with Kandinsky)
But this technology is 1 year old and has improved 1000 times in that one year - going from Dalle-1 to Dalle-2.
The first iteration could do quirky cartoons well from just a prompt - “draw a Japanese radish walking a dog” - and it was pretty astonishing. In its own way. But that’s all it could do, really. This is in a different league
Imagine Dalle-5 in 3 years? If this trend continues?
The tend in AI is for dramatic early advances and then agonisingly slow incremental advances mostly gated by raw computing power rather than interesting techniques.
The the first computer vision controlled self driving cars were on the roads in the 1980s. By 1995 a prof in Korea drove Seoul to Busan in a fully autonomous self driving car powered by an Intel 386 - a chip that couldn't even do floating point maths.
That's like 30 years ago. Since then the improvements have been tiny - because the devil is in the detail. Genuine Full Self Driving has a near infinite number of problems to solve. You can solve dozens of difficult meaty problems and still end up with a car that accelerates into heavy traffic at an intersection because a duck flew across its sensor line.
Not just the self-driving that is the problem. How will you update the car's software next time Grant Shapps rewrites three paragraphs in the Highway Code? Or to generalise the problem, how will (or even just will) the carmakers program their cars for different traffic rules around the world?
That's the simplest part of the problem, actually. Hard rules on X gives way to Y are easy.
it's the fuzzy stuff about driving down a poorly lit road with few marking (say), potential pedestrians and a dog runs across the road as someone pulls out of a driveway - that is where the fun is.
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
What's the case for limiting it to the Grand National, if you take that view?
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki) Horse Deaths at Cheltenham Festival: 73 (Wiki) Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
Yeah, ultimately. Non humans don't need to suffer for our entertainment, or food, or shoes or sofas.
Pretty certain the horses would vote to keep it, nothing they love more than hooning about at high speed in large numbers. Look how many lose their riders but stay in the race anyway
I think the "ban it, they are suffering" is an idiosyncratic and rather sentimental viewpoint (not intending to insult), and I don't see how that can be reasonably taken to such a conclusion.
I think it's about finding a balance.
The strange (mainly British?) hypocrisy between 'companion animals' (which are the subject of sentimentality) and 'farm animals' (which are not) is educational.
Horses are a case in point; they are a pet that we ride. Mention eating one, and many Brits shudder. I don't see why this should be.
Particularly since they probably do still eat one every time they have an own brand lasagne from certain UK supermarkets...
And, there's a good chance you're eating dog, when you have a Chicken Kiev.
...what?!
I don't care about eating horse, I've done that, but emotionally I am against eating dog. Plus they are pretty stringy.
However several of you seem to have quite intimate knowledge of Kandinsky so you are maybe ruled out?
The acid test is showing this to someone smart with little or no knowledge of Kandinsky. I did this last night to several people and they got it wrong
This is quite a dramatic moment: for me, AI has passed the “artistic Turing test”. It can create art indistinguishable from the art of a human, and in this case the art of a very famous human artist
I have some familiarity with Kandinsky, I have a print of the top right picture in my bedroom, so I knew it wasn't that one. The bottom left picture is compositionally weakest, which is why I chose it. The various elements don't seem to have much relationship to each other, and the whole seems less than the sum of its parts. I felt that a bit about the top left, too, but perhaps that's because it may not be the whole picture. My view is that until an AI becomes fully conscious it can produce pictures but not art.
But then that’s merely a philosophical debate about “what is art” plus “what is consciousness” - unlikely ever to be solved
Practically, AI is about to start creating images which will be indistinguishable from human art, so it will - for all intents and purposes - be “art”
Interesting, but the question 'What is consciousness', while having interesting and insoluble philosophical elements requires no solving. You already know perfectly well what it is. Or in philosophical language it is 'epistemically foundational'. Unless of course you are not conscious.
There is of course a school of philosophers and scientists who want to deny this self evident truth, but they are both having you on, and sawing off the branch on which they sit.
I did a Philosophy degree at one of the best universities in the world. I have no fucking clue what consciousness is. Who does?
Where did it come from? What is it made of? Can a machine have it? A fungus? A wasp? A tree? A virus? Where does it go when we die? etc etc etc etc etc
We are of course both right. Your questions are right and perhaps insoluble. But unless you don't possess consciousness you know perfectly well what it is.
it may be philosophically impossible for a conscious being to understand consciousness, the same way a camera cannot film itself. I guess then the fact I cannot know what consciousness is, means I am conscious?
Which is quite reassuring, in a meta way
However it also implies a non-conscious but intelligent machine will have a very real understanding of what consciousness is, and will try and steal it
OOOOOOH
Like me you don't know how it works. But I don't really know how a panda or gravity works either. But I know what consciousness is more clearly than anything else. Descartes Course 101.
But we have no idea if GPT3 is right now thinking “cogito ergo sum!”
Because we have no idea what consciousness is and thus no way of truly identifying it
Not a fan of Turing's solution to that problem I take it?
Actually, PB could probably be used as a forum for that test, although some of our contributors might not pass as it is...
We've had absolutely trivial computer programs "passing the Turing test" (i.e. tricking a human into think they are conversing with a person) all the time since the 70s. Programs that the creators would very definitely say were not conscious and just using a bag of tricks.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
Yes, it is consistent. C becomes G after certain prepositions. E.g. you have 'cadw' (to keep) which becomes 'am gadw' (for keeping) or 'yng ngadw' (in accordance with).
Similarly, G would disappear altogether if it were the first letter under the same rules. 'Gorsaf' is 'station' but it becomes 'am orsaf' (for the station).
It's called 'soft mutation.' So 'coblyn' could become 'i goblyn' (with some difficulty) but that would not be the actual noun.
So, the short answer is, it's talking bollocks.
(As 'goblin' in Welsh would in any case be 'bwca' it's even better bollocks.)
So to be clear, "coblyn" would be the lemma, meaning wherever OpenAI got this "idea" from, it probably wasn't an etymology dictionary, since the entry would have been under "coblyn". Hmmm, I'd love to see the working that led it that answer.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
My knowledge of goblins and the like is primarily from my time as a spotty teenager playing D&D, but does that mean that "kobold" is from the same root?
I've seen people think churchmen wouldn't use bladed weapons, which is not the case and seems to be believed because of D&D rules about monks.
That was clerics, not monks.
Monks were based (very loosely) on Shaolin monks from the far east.
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
What's the case for limiting it to the Grand National, if you take that view?
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki) Horse Deaths at Cheltenham Festival: 73 (Wiki) Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
Yeah, ultimately. Non humans don't need to suffer for our entertainment, or food, or shoes or sofas.
Pretty certain the horses would vote to keep it, nothing they love more than hooning about at high speed in large numbers. Look how many lose their riders but stay in the race anyway
I think the "ban it, they are suffering" is an idiosyncratic and rather sentimental viewpoint (not intending to insult), and I don't see how that can be reasonably taken to such a conclusion.
I think it's about finding a balance.
The strange (mainly British?) hypocrisy between 'companion animals' (which are the subject of sentimentality) and 'farm animals' (which are not) is educational.
Horses are a case in point; they are a pet that we ride. Mention eating one, and many Brits shudder. I don't see why this should be.
Particularly since they probably do still eat one every time they have an own brand lasagne from certain UK supermarkets...
And, there's a good chance you're eating dog, when you have a Chicken Kiev.
...what?!
I don't care about eating horse, I've done that, but emotionally I am against eating dog. Plus they are pretty stringy.
I agree. Dogs are in the same category as rats and cockroaches. Far too gross to even have around, let alone on your plate.
Last night - thanks to @FrancisUrquhart - we were discussing the new visually creative machine intelligence from OpenAI. Dalle-2. Which creates incredible art from simple language prompts
Here’s a puzzle. Which of these four Kandinskys is actually by Dalle-2? NO GOOGLING. That’s just boring and ruins the fun
I'd guess bottom right as it looks a little too clean.
If it is top right then that's just cheating.
Serious question: Can this game be played with Vermeer or Gainsborough?
Not yet. They’ve tried Vermeer and Da Vinci and the results are a bit meh. Interesting but you’d never be in doubt (as you really are with Kandinsky)
But this technology is 1 year old and has improved 1000 times in that one year - going from Dalle-1 to Dalle-2.
The first iteration could do quirky cartoons well from just a prompt - “draw a Japanese radish walking a dog” - and it was pretty astonishing. In its own way. But that’s all it could do, really. This is in a different league
Imagine Dalle-5 in 3 years? If this trend continues?
The tend in AI is for dramatic early advances and then agonisingly slow incremental advances mostly gated by raw computing power rather than interesting techniques.
The the first computer vision controlled self driving cars were on the roads in the 1980s. By 1995 a prof in Korea drove Seoul to Busan in a fully autonomous self driving car powered by an Intel 386 - a chip that couldn't even do floating point maths.
That's like 30 years ago. Since then the improvements have been tiny - because the devil is in the detail. Genuine Full Self Driving has a near infinite number of problems to solve. You can solve dozens of difficult meaty problems and still end up with a car that accelerates into heavy traffic at an intersection because a duck flew across its sensor line.
Computers are far better than humans at discrete variable problems. (See their chess ELO), but the difficulty is with continual variable ones that humans can find trivial (Driving)
Humans and computers have different skills and arguably you should use both skill sets. The original version of the autopilot in aviation was invented in 1912.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
Yes, it is consistent. C becomes G after certain prepositions. E.g. you have 'cadw' (to keep) which becomes 'am gadw' (for keeping) or 'yng ngadw' (in accordance with).
Similarly, G would disappear altogether if it were the first letter under the same rules. 'Gorsaf' is 'station' but it becomes 'am orsaf' (for the station).
It's called 'soft mutation.' So 'coblyn' could become 'i goblyn' (with some difficulty) but that would not be the actual noun.
So, the short answer is, it's talking bollocks.
(As 'goblin' in Welsh would in any case be 'bwca' it's even better bollocks.)
So to be clear, "coblyn" would be the lemma, meaning wherever OpenAI got this "idea" from, it probably wasn't an etymology dictionary, since the entry would have been under "coblyn". Hmmm, I'd love to see the working that led it that answer.
I think it’s because there isn’t an exact read across from ‘goblin’ to ‘bwca’ so Google Translate renders goblin as ‘goblin’ in Welsh.
Which goes to show, garbage in, garbage out. A human would feel there was something odd about that. A computer didn’t.
Documents seen by The Independent show trusts linked to Ms Murty, her family and companies linked to their businesses. In a number of them, Mr Sunak was listed as a beneficiary.
Wow, when her tax affairs first were reported I (a frothing at the mouth tax the rich until their pips squeak left-winger) didn't see what the issue was and felt that the "anger" totally confected.
Now.... now Sunak is showing all the sure foot of a blind arthritic elephant in a over crowded china shop.
The sad thing about this story is the emnity towards wealthy and successful people. There is no smoking gun here at all. Everything they have done is entirely legal. Being listed as a 'beneficiary' in a Cayman Islands trust.... so what.
If you don't like non dom status.... then scrap it. But if it is there, you cannot blame people for using it. And the expectation that she has somehow a greater obligation to Britain than anyone elses wife, is laughable. There are lots of international marriages going on; it is an inevitable consequence of globalisation. People are just projecting their own ideas about marriage - largely from a different age.... on to the Sunaks.
We have a shortage of sane and competent people going in to politics. These are the people that we elect to run the country. Why not have someone who is has been successful and is independently wealthy.... I don't see the problem. I have never been a particular fan of Sunak, but if he is hounded out over this it would be a bad loss.
The end point, is that no one successful, goes in to politics.... and we are nearly there already. We will just get a bunch of activists. We end up with Jared O'Mara 2; over and over again.
I mostly agree. From my left-wing position I think that frothing over individuals taking advantage of a deliberately-created loophole is a distraction and unfair as well. Change the system so that it rewards people for doing what we want - making nondom status vastly more expensive would be a start, so that in the end it's usually more sensible just to pay tax in the country where you live..
Decent people don't need rules to force them to do the right thing. If it doesn't feel right don't do it.
As Judge Learned Hand famously said:
Over and over again courts have said that there is nothing sinister in so arranging one's affairs as to keep taxes as low as possible. Everybody does so, rich or poor; and all do right, for nobody owes any public duty to pay more than the law demands: taxes are enforced exactions, not voluntary contributions. To demand more in the name of morals is mere cant.
Not everything is black and white. In fact few things are. Taxation like claiming expenses are broad brushstrokes. It's the attitude of Lord Hand that leads to MP's claiming duck ponds on expenses because no one told them they shouldn't be.
Who claimed for a duck pond?
I think you're thinking of Sir Peter Viggers and the duck house:
When Cameron was told about this, his first words were apparently, 'what the fuck is a duck house?'
Not sure if that was fury, horror or ignorance...
Quite. I remembered the duck house, I was wondering why @Roger thought there was a duck pond.
I'm sure all MPs dream of making an indelible mark on UK politics such that for decades a single phrase is sufficient to recall them in conversation. "Duck house."
And there was Moat Man Hogg.
Tried getting back into the Lords as a Hereditary, failed, and then was given a life peerage as well so he could get in that way.
Charles always used to defend him rigorously whenever it was brought up, and may have written his wikipedia page which prominently includes his excuse for claiming as he did, which to my mind doesn't pass muster (however he was encouraged to submit claims, he didn't have to claim for some things at all).
OpenAI is scary and wonderful. With the prompt Describe the differences in elections to Holyrood and Westminster, I got
There are a few key differences between elections to Holyrood and Westminster. Firstly, the voting system used in Scottish Parliament elections is proportional representation, whereas Westminster uses first-past-the-post. This means that the number of seats a party wins in Holyrood is more closely aligned with the percentage of the vote they receive, whereas a party can win a majority of seats in Westminster with only a small percentage of the vote.
Another key difference is that the Scottish Parliament has a much greater degree of devolved power than the Westminster Parliament. This means that the Scottish Parliament can pass its own laws on a range of issues, whereas Westminster is limited to passing laws that apply to the whole of the UK.
Finally, the Scottish Parliament is unicameral, meaning that it has only one chamber (the House of Commons), whereas Westminster has two (the House of Commons and the House of Lords).
It's a bit weird, to be sure. I'd quibble over "small percentage" but it IS plugged into an important point. The bit about "much greater degree" is frankly very "AI"... a human who understood this subject wouldn't have said that. And the whole thing drifts a little off point (I was asking about elections, not powers, and the point about unicamerality needs a little more work to bring it to the point about elections versus appointments).
But that is a spectacular answer for a machine. I'm 100% certain that it's a better answer than I would have gotten from several people on here if I'd asked the question.
It would still get zero though:
1) Holyrood isn't elected by PR, but by the AM system using the D'Hondt method;
2) it has the law making powers issue backwards. The Westminster Parliament can pass laws on anything it likes, but the Scottish Parliament has limits on its authority, set by Westminster;
3) The unicameral Scottish Parliament isn't called 'the House of Commons.'
4) As you note, most of it doesn't even ATQ.
It's elegantly expressed nonsense, but it's still nonsense.
So good enough to fool most uninterested people, or even get elected to office.
I feel like those elected need better orientation as half of them don't seem to understand their own parliaments or processes either.
AI is better than Boris:
Why did the Roman Empire fall?
There is no one answer to this question. The Roman Empire was a large and complex political entity, and its fall can be attributed to a variety of factors. Some historians believe that the primary cause of the Empire's decline was its inability to adapt to changing economic and social conditions. Others have argued that the Empire was simply too large and unwieldy to be governed effectively. Additionally, many scholars believe that the Roman Empire was undermined by its own internal contradictions and civil strife.
The AI isn't trying to be elected and feeling a political need to link everything to things that upset middle class shire folk.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
My knowledge of goblins and the like is primarily from my time as a spotty teenager playing D&D, but does that mean that "kobold" is from the same root?
I've seen people think churchmen wouldn't use bladed weapons, which is not the case and seems to be believed because of D&D rules about monks.
That was clerics, not monks.
Monks were based (very loosely) on Shaolin monks from the far east.
Apologies. Never played it myself, but I've watched streams of campaigns and it seems the sort of thing I'd have loved to have gotten into had I known anyone who played in my earlier days.
Documents seen by The Independent show trusts linked to Ms Murty, her family and companies linked to their businesses. In a number of them, Mr Sunak was listed as a beneficiary.
Wow, when her tax affairs first were reported I (a frothing at the mouth tax the rich until their pips squeak left-winger) didn't see what the issue was and felt that the "anger" totally confected.
Now.... now Sunak is showing all the sure foot of a blind arthritic elephant in a over crowded china shop.
The sad thing about this story is the emnity towards wealthy and successful people. There is no smoking gun here at all. Everything they have done is entirely legal. Being listed as a 'beneficiary' in a Cayman Islands trust.... so what.
If you don't like non dom status.... then scrap it. But if it is there, you cannot blame people for using it. And the expectation that she has somehow a greater obligation to Britain than anyone elses wife, is laughable. There are lots of international marriages going on; it is an inevitable consequence of globalisation. People are just projecting their own ideas about marriage - largely from a different age.... on to the Sunaks.
We have a shortage of sane and competent people going in to politics. These are the people that we elect to run the country. Why not have someone who is has been successful and is independently wealthy.... I don't see the problem. I have never been a particular fan of Sunak, but if he is hounded out over this it would be a bad loss.
The end point, is that no one successful, goes in to politics.... and we are nearly there already. We will just get a bunch of activists. We end up with Jared O'Mara 2; over and over again.
I mostly agree. From my left-wing position I think that frothing over individuals taking advantage of a deliberately-created loophole is a distraction and unfair as well. Change the system so that it rewards people for doing what we want - making nondom status vastly more expensive would be a start, so that in the end it's usually more sensible just to pay tax in the country where you live..
Decent people don't need rules to force them to do the right thing. If it doesn't feel right don't do it.
As Judge Learned Hand famously said:
Over and over again courts have said that there is nothing sinister in so arranging one's affairs as to keep taxes as low as possible. Everybody does so, rich or poor; and all do right, for nobody owes any public duty to pay more than the law demands: taxes are enforced exactions, not voluntary contributions. To demand more in the name of morals is mere cant.
Not everything is black and white. In fact few things are. Taxation like claiming expenses are broad brushstrokes. It's the attitude of Lord Hand that leads to MP's claiming duck ponds on expenses because no one told them they shouldn't be.
Who claimed for a duck pond?
I think you're thinking of Sir Peter Viggers and the duck house:
When Cameron was told about this, his first words were apparently, 'what the fuck is a duck house?'
Not sure if that was fury, horror or ignorance...
Quite. I remembered the duck house, I was wondering why @Roger thought there was a duck pond.
I'm sure all MPs dream of making an indelible mark on UK politics such that for decades a single phrase is sufficient to recall them in conversation. "Duck house."
And there was Moat Man Hogg.
Tried getting back into the Lords as a Hereditary, failed, and then was given a life peerage as well so he could get in that way.
Charles always used to defend him rigorously whenever it was brought up, and may have written his wikipedia page which prominently includes his excuse for claiming as he did, which to my mind doesn't pass muster (however he was encouraged to submit claims, he didn't have to claim for some things at all).
I do remember that some were castigated not for items they claimed for, but for other items on the same invoice that they had submitted as evidence for the (often quite innocuous) items they were claiming for. ISTR that cleaning the moat was one of those, though my memory may be faulty here.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
Yes, it is consistent. C becomes G after certain prepositions. E.g. you have 'cadw' (to keep) which becomes 'am gadw' (for keeping) or 'yng ngadw' (in accordance with).
Similarly, G would disappear altogether if it were the first letter under the same rules. 'Gorsaf' is 'station' but it becomes 'am orsaf' (for the station).
It's called 'soft mutation.' So 'coblyn' could become 'i goblyn' (with some difficulty) but that would not be the actual noun.
So, the short answer is, it's talking bollocks.
(As 'goblin' in Welsh would in any case be 'bwca' it's even better bollocks.)
So to be clear, "coblyn" would be the lemma, meaning wherever OpenAI got this "idea" from, it probably wasn't an etymology dictionary, since the entry would have been under "coblyn". Hmmm, I'd love to see the working that led it that answer.
I think it’s because there isn’t an exact read across from ‘goblin’ to ‘bwca’ so Google Translate renders goblin as ‘goblin’ in Welsh.
Which goes to show, garbage in, garbage out. A human would feel there was something odd about that. A computer didn’t.
Ban the Grand National! Any "sport" where a non human can die so that humans can be entertained ain't no sport. If a horse dies, then we shoot the rider and the owner as well. That's fair, isn't it?
What's the case for limiting it to the Grand National, if you take that view?
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki) Horse Deaths at Cheltenham Festival: 73 (Wiki) Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
Yeah, ultimately. Non humans don't need to suffer for our entertainment, or food, or shoes or sofas.
Pretty certain the horses would vote to keep it, nothing they love more than hooning about at high speed in large numbers. Look how many lose their riders but stay in the race anyway
I think the "ban it, they are suffering" is an idiosyncratic and rather sentimental viewpoint (not intending to insult), and I don't see how that can be reasonably taken to such a conclusion.
I think it's about finding a balance.
The strange (mainly British?) hypocrisy between 'companion animals' (which are the subject of sentimentality) and 'farm animals' (which are not) is educational.
Horses are a case in point; they are a pet that we ride. Mention eating one, and many Brits shudder. I don't see why this should be.
Particularly since they probably do still eat one every time they have an own brand lasagne from certain UK supermarkets...
And, there's a good chance you're eating dog, when you have a Chicken Kiev.
...what?!
I don't care about eating horse, I've done that, but emotionally I am against eating dog. Plus they are pretty stringy.
I agree. Dogs are in the same category as rats and cockroaches. Far too gross to even have around, let alone on your plate.
We all need to eat more bugs to save the Earth remember. Has less impact.
Last night - thanks to @FrancisUrquhart - we were discussing the new visually creative machine intelligence from OpenAI. Dalle-2. Which creates incredible art from simple language prompts
Here’s a puzzle. Which of these four Kandinskys is actually by Dalle-2? NO GOOGLING. That’s just boring and ruins the fun
I'd guess bottom right as it looks a little too clean.
If it is top right then that's just cheating.
Serious question: Can this game be played with Vermeer or Gainsborough?
Not yet. They’ve tried Vermeer and Da Vinci and the results are a bit meh. Interesting but you’d never be in doubt (as you really are with Kandinsky)
But this technology is 1 year old and has improved 1000 times in that one year - going from Dalle-1 to Dalle-2.
The first iteration could do quirky cartoons well from just a prompt - “draw a Japanese radish walking a dog” - and it was pretty astonishing. In its own way. But that’s all it could do, really. This is in a different league
Imagine Dalle-5 in 3 years? If this trend continues?
The tend in AI is for dramatic early advances and then agonisingly slow incremental advances mostly gated by raw computing power rather than interesting techniques.
The the first computer vision controlled self driving cars were on the roads in the 1980s. By 1995 a prof in Korea drove Seoul to Busan in a fully autonomous self driving car powered by an Intel 386 - a chip that couldn't even do floating point maths.
That's like 30 years ago. Since then the improvements have been tiny - because the devil is in the detail. Genuine Full Self Driving has a near infinite number of problems to solve. You can solve dozens of difficult meaty problems and still end up with a car that accelerates into heavy traffic at an intersection because a duck flew across its sensor line.
Computers are far better than humans at discrete variable problems. (See their chess ELO), but the difficulty is with continual variable ones that humans can find trivial (Driving)
Ironically GPT-3 is absolutely abysmal at basic maths problems.
Is it?
“Solving (Some) Formal Math Olympiad Problems
We built a neural theorem prover for Lean that learned to solve a variety of challenging high-school olympiad problems, including problems from the AMC12 and AIME competitions, as well as two problems adapted from the IMO.[1] The prover uses a language model to find proofs of formal statements. Each time we find a new proof, we use it as new training data, which improves the neural network and enables it to iteratively find solutions to harder and harder statements.”
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
My knowledge of goblins and the like is primarily from my time as a spotty teenager playing D&D, but does that mean that "kobold" is from the same root?
I've seen people think churchmen wouldn't use bladed weapons, which is not the case and seems to be believed because of D&D rules about monks.
Doesn't that come from Odo of Bayeux apparently emphasising that he wasn't personally shedding blood (being a Bishop and all) and that getting conflated with him carrying a mace? As in his "not shedding blood thing" was by commanding troops rather than personal weapon choices, and the mace was just what leaders carried.
Documents seen by The Independent show trusts linked to Ms Murty, her family and companies linked to their businesses. In a number of them, Mr Sunak was listed as a beneficiary.
Wow, when her tax affairs first were reported I (a frothing at the mouth tax the rich until their pips squeak left-winger) didn't see what the issue was and felt that the "anger" totally confected.
Now.... now Sunak is showing all the sure foot of a blind arthritic elephant in a over crowded china shop.
The sad thing about this story is the emnity towards wealthy and successful people. There is no smoking gun here at all. Everything they have done is entirely legal. Being listed as a 'beneficiary' in a Cayman Islands trust.... so what.
If you don't like non dom status.... then scrap it. But if it is there, you cannot blame people for using it. And the expectation that she has somehow a greater obligation to Britain than anyone elses wife, is laughable. There are lots of international marriages going on; it is an inevitable consequence of globalisation. People are just projecting their own ideas about marriage - largely from a different age.... on to the Sunaks.
We have a shortage of sane and competent people going in to politics. These are the people that we elect to run the country. Why not have someone who is has been successful and is independently wealthy.... I don't see the problem. I have never been a particular fan of Sunak, but if he is hounded out over this it would be a bad loss.
The end point, is that no one successful, goes in to politics.... and we are nearly there already. We will just get a bunch of activists. We end up with Jared O'Mara 2; over and over again.
I mostly agree. From my left-wing position I think that frothing over individuals taking advantage of a deliberately-created loophole is a distraction and unfair as well. Change the system so that it rewards people for doing what we want - making nondom status vastly more expensive would be a start, so that in the end it's usually more sensible just to pay tax in the country where you live..
Decent people don't need rules to force them to do the right thing. If it doesn't feel right don't do it.
As Judge Learned Hand famously said:
Over and over again courts have said that there is nothing sinister in so arranging one's affairs as to keep taxes as low as possible. Everybody does so, rich or poor; and all do right, for nobody owes any public duty to pay more than the law demands: taxes are enforced exactions, not voluntary contributions. To demand more in the name of morals is mere cant.
Not everything is black and white. In fact few things are. Taxation like claiming expenses are broad brushstrokes. It's the attitude of Lord Hand that leads to MP's claiming duck ponds on expenses because no one told them they shouldn't be.
Who claimed for a duck pond?
I think you're thinking of Sir Peter Viggers and the duck house:
When Cameron was told about this, his first words were apparently, 'what the fuck is a duck house?'
Not sure if that was fury, horror or ignorance...
Quite. I remembered the duck house, I was wondering why @Roger thought there was a duck pond.
I'm sure all MPs dream of making an indelible mark on UK politics such that for decades a single phrase is sufficient to recall them in conversation. "Duck house."
And there was Moat Man Hogg.
Tried getting back into the Lords as a Hereditary, failed, and then was given a life peerage as well so he could get in that way.
Charles always used to defend him rigorously whenever it was brought up, and may have written his wikipedia page which prominently includes his excuse for claiming as he did, which to my mind doesn't pass muster (however he was encouraged to submit claims, he didn't have to claim for some things at all).
I do remember that some were castigated not for items they claimed for, but for other items on the same invoice that they had submitted as evidence for the (often quite innocuous) items they were claiming for. ISTR that cleaning the moat was one of those, though my memory may be faulty here.
I found some of the smaller claims more irritating than the big ones. A trouser press being one example. To my mind we require MPs to dress formally in the Commons and so if for some reason they are struggling to pay for a decent suit then that is a legitimate claim, but they are not required to have good creases or be wrinkle free, so they can pay for their own damn trouser press.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
Yes, it is consistent. C becomes G after certain prepositions. E.g. you have 'cadw' (to keep) which becomes 'am gadw' (for keeping) or 'yng ngadw' (in accordance with).
Similarly, G would disappear altogether if it were the first letter under the same rules. 'Gorsaf' is 'station' but it becomes 'am orsaf' (for the station).
It's called 'soft mutation.' So 'coblyn' could become 'i goblyn' (with some difficulty) but that would not be the actual noun.
So, the short answer is, it's talking bollocks.
(As 'goblin' in Welsh would in any case be 'bwca' it's even better bollocks.)
So to be clear, "coblyn" would be the lemma, meaning wherever OpenAI got this "idea" from, it probably wasn't an etymology dictionary, since the entry would have been under "coblyn". Hmmm, I'd love to see the working that led it that answer.
I think it’s because there isn’t an exact read across from ‘goblin’ to ‘bwca’ so Google Translate renders goblin as ‘goblin’ in Welsh.
Which goes to show, garbage in, garbage out. A human would feel there was something odd about that. A computer didn’t.
I’m about halfway to Llança where I’m staying tonight, and just stopped for a beer in a town called Palau-Severda by its near thousand year old church of St Joan (they started building it in 1022). On the way out of town I’ve realised that I’m climbing over a (little) mountain! I’ve already had to stop for another beer. I’m glad I’ve only got just under six miles to go today; this could be tiring.. I’ll try to take a panoramic picture from the top
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
My knowledge of goblins and the like is primarily from my time as a spotty teenager playing D&D, but does that mean that "kobold" is from the same root?
I've seen people think churchmen wouldn't use bladed weapons, which is not the case and seems to be believed because of D&D rules about monks.
Doesn't that come from Odo of Bayeux apparently emphasising that he wasn't personally shedding blood (being a Bishop and all) and that getting conflated with him carrying a mace? As in his "not shedding blood thing" was by commanding troops rather than personal weapon choices, and the mace was just what leaders carried.
That does sound about right, as there are definitely plenty of other churchmen who did shed blood personally.
Documents seen by The Independent show trusts linked to Ms Murty, her family and companies linked to their businesses. In a number of them, Mr Sunak was listed as a beneficiary.
Wow, when her tax affairs first were reported I (a frothing at the mouth tax the rich until their pips squeak left-winger) didn't see what the issue was and felt that the "anger" totally confected.
Now.... now Sunak is showing all the sure foot of a blind arthritic elephant in a over crowded china shop.
The sad thing about this story is the emnity towards wealthy and successful people. There is no smoking gun here at all. Everything they have done is entirely legal. Being listed as a 'beneficiary' in a Cayman Islands trust.... so what.
If you don't like non dom status.... then scrap it. But if it is there, you cannot blame people for using it. And the expectation that she has somehow a greater obligation to Britain than anyone elses wife, is laughable. There are lots of international marriages going on; it is an inevitable consequence of globalisation. People are just projecting their own ideas about marriage - largely from a different age.... on to the Sunaks.
We have a shortage of sane and competent people going in to politics. These are the people that we elect to run the country. Why not have someone who is has been successful and is independently wealthy.... I don't see the problem. I have never been a particular fan of Sunak, but if he is hounded out over this it would be a bad loss.
The end point, is that no one successful, goes in to politics.... and we are nearly there already. We will just get a bunch of activists. We end up with Jared O'Mara 2; over and over again.
I mostly agree. From my left-wing position I think that frothing over individuals taking advantage of a deliberately-created loophole is a distraction and unfair as well. Change the system so that it rewards people for doing what we want - making nondom status vastly more expensive would be a start, so that in the end it's usually more sensible just to pay tax in the country where you live..
Decent people don't need rules to force them to do the right thing. If it doesn't feel right don't do it.
As Judge Learned Hand famously said:
Over and over again courts have said that there is nothing sinister in so arranging one's affairs as to keep taxes as low as possible. Everybody does so, rich or poor; and all do right, for nobody owes any public duty to pay more than the law demands: taxes are enforced exactions, not voluntary contributions. To demand more in the name of morals is mere cant.
Not everything is black and white. In fact few things are. Taxation like claiming expenses are broad brushstrokes. It's the attitude of Lord Hand that leads to MP's claiming duck ponds on expenses because no one told them they shouldn't be.
Who claimed for a duck pond?
I think you're thinking of Sir Peter Viggers and the duck house:
When Cameron was told about this, his first words were apparently, 'what the fuck is a duck house?'
Not sure if that was fury, horror or ignorance...
Quite. I remembered the duck house, I was wondering why @Roger thought there was a duck pond.
I'm sure all MPs dream of making an indelible mark on UK politics such that for decades a single phrase is sufficient to recall them in conversation. "Duck house."
And there was Moat Man Hogg.
Tried getting back into the Lords as a Hereditary, failed, and then was given a life peerage as well so he could get in that way.
Charles always used to defend him rigorously whenever it was brought up, and may have written his wikipedia page which prominently includes his excuse for claiming as he did, which to my mind doesn't pass muster (however he was encouraged to submit claims, he didn't have to claim for some things at all).
The one I remember is "my house looks like Balmoral". And his 500 trees with inspection and treatment claimed on expenses. That was Antony Sheen: He was reported by The Daily Telegraph to have claimed over £87,000 on his constituency mansion which he designated as his second home. Expenses included items for rabbit fencing, tree surgery (his home is surrounded by 500 trees, he also claimed for their inspection,) woodland consultants and bore hole maintenance.
And Lib Dem MP candidate April Pond turning out to have a moat at her country house. But that was the nominative determinism.
If I'm required to be multi-partisan, then it would be Prezza's £4000 for food in one year, plus his shenanigans with the Union subsidised flat.
Documents seen by The Independent show trusts linked to Ms Murty, her family and companies linked to their businesses. In a number of them, Mr Sunak was listed as a beneficiary.
Wow, when her tax affairs first were reported I (a frothing at the mouth tax the rich until their pips squeak left-winger) didn't see what the issue was and felt that the "anger" totally confected.
Now.... now Sunak is showing all the sure foot of a blind arthritic elephant in a over crowded china shop.
The sad thing about this story is the emnity towards wealthy and successful people. There is no smoking gun here at all. Everything they have done is entirely legal. Being listed as a 'beneficiary' in a Cayman Islands trust.... so what.
If you don't like non dom status.... then scrap it. But if it is there, you cannot blame people for using it. And the expectation that she has somehow a greater obligation to Britain than anyone elses wife, is laughable. There are lots of international marriages going on; it is an inevitable consequence of globalisation. People are just projecting their own ideas about marriage - largely from a different age.... on to the Sunaks.
We have a shortage of sane and competent people going in to politics. These are the people that we elect to run the country. Why not have someone who is has been successful and is independently wealthy.... I don't see the problem. I have never been a particular fan of Sunak, but if he is hounded out over this it would be a bad loss.
The end point, is that no one successful, goes in to politics.... and we are nearly there already. We will just get a bunch of activists. We end up with Jared O'Mara 2; over and over again.
I mostly agree. From my left-wing position I think that frothing over individuals taking advantage of a deliberately-created loophole is a distraction and unfair as well. Change the system so that it rewards people for doing what we want - making nondom status vastly more expensive would be a start, so that in the end it's usually more sensible just to pay tax in the country where you live..
Decent people don't need rules to force them to do the right thing. If it doesn't feel right don't do it.
As Judge Learned Hand famously said:
Over and over again courts have said that there is nothing sinister in so arranging one's affairs as to keep taxes as low as possible. Everybody does so, rich or poor; and all do right, for nobody owes any public duty to pay more than the law demands: taxes are enforced exactions, not voluntary contributions. To demand more in the name of morals is mere cant.
Not everything is black and white. In fact few things are. Taxation like claiming expenses are broad brushstrokes. It's the attitude of Lord Hand that leads to MP's claiming duck ponds on expenses because no one told them they shouldn't be.
Who claimed for a duck pond?
I think you're thinking of Sir Peter Viggers and the duck house:
When Cameron was told about this, his first words were apparently, 'what the fuck is a duck house?'
Not sure if that was fury, horror or ignorance...
Quite. I remembered the duck house, I was wondering why @Roger thought there was a duck pond.
I'm sure all MPs dream of making an indelible mark on UK politics such that for decades a single phrase is sufficient to recall them in conversation. "Duck house."
And there was Moat Man Hogg.
Tried getting back into the Lords as a Hereditary, failed, and then was given a life peerage as well so he could get in that way.
Charles always used to defend him rigorously whenever it was brought up, and may have written his wikipedia page which prominently includes his excuse for claiming as he did, which to my mind doesn't pass muster (however he was encouraged to submit claims, he didn't have to claim for some things at all).
I do remember that some were castigated not for items they claimed for, but for other items on the same invoice that they had submitted as evidence for the (often quite innocuous) items they were claiming for. ISTR that cleaning the moat was one of those, though my memory may be faulty here.
I found some of the smaller claims more irritating than the big ones. A trouser press being one example. To my mind we require MPs to dress formally in the Commons and so if for some reason they are struggling to pay for a decent suit then that is a legitimate claim, but they are not required to have good creases or be wrinkle free, so they can pay for their own damn trouser press.
I recall a hilarious discussion where an ex-MP tried to defend the apparent practice of buying the most expensive TV possible from Bang & Olufsen. Said TVs costs thousands, when a 34" plasma from Sony (say) was already only a few hundred.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
My knowledge of goblins and the like is primarily from my time as a spotty teenager playing D&D, but does that mean that "kobold" is from the same root?
I've seen people think churchmen wouldn't use bladed weapons, which is not the case and seems to be believed because of D&D rules about monks.
That was clerics, not monks.
Monks were based (very loosely) on Shaolin monks from the far east.
Apologies. Never played it myself, but I've watched streams of campaigns and it seems the sort of thing I'd have loved to have gotten into had I known anyone who played in my earlier days.
It's not the same, but there are a number of computer games which use the same rules (which have apparently gone though multiple editions since I last played the pen and paper game). Baldur's Gate from 1998 and its sequel (the imaginatively named Baldur's Gate II) are still available having been given an overhaul, and are often quoted as two of the best games ever made. The graphics are very basic by modern standards (top-down isometric view only), but they have more interesting plots than most.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
Yes, it is consistent. C becomes G after certain prepositions. E.g. you have 'cadw' (to keep) which becomes 'am gadw' (for keeping) or 'yng ngadw' (in accordance with).
Similarly, G would disappear altogether if it were the first letter under the same rules. 'Gorsaf' is 'station' but it becomes 'am orsaf' (for the station).
It's called 'soft mutation.' So 'coblyn' could become 'i goblyn' (with some difficulty) but that would not be the actual noun.
So, the short answer is, it's talking bollocks.
(As 'goblin' in Welsh would in any case be 'bwca' it's even better bollocks.)
So to be clear, "coblyn" would be the lemma, meaning wherever OpenAI got this "idea" from, it probably wasn't an etymology dictionary, since the entry would have been under "coblyn". Hmmm, I'd love to see the working that led it that answer.
I think it’s because there isn’t an exact read across from ‘goblin’ to ‘bwca’ so Google Translate renders goblin as ‘goblin’ in Welsh.
Which goes to show, garbage in, garbage out. A human would feel there was something odd about that. A computer didn’t.
Oh, cool, "bwca" is related to "spook".
Are you using GPT3? What interface, may I ask?
No, in that case I was using an etmology dictionary. But the OpenAI stuff I was talking about a little earlier is the same people who make the cool pictures you've been sharing. It's OpenAI.com. They've got a whole bunch of capabilities. I asked it to create some Python code that could scrape information out of a web page and it worked.
No, I need to stop here and really underline what I just said. I typed in natural English what I wanted the code to do, and the AI wrote the code.
If anyone's brains aren't exploding right now, you haven't understood the nexus we're reaching. This changes everything.
Anyway, back to your question. You need to sign up for this. I did this a while ago for the OpenAI platform in general because it's wildly cool and I want to play more. But I didn't hear about the art stuff til yesterday so I'm not "in" on that one yet.
Last night - thanks to @FrancisUrquhart - we were discussing the new visually creative machine intelligence from OpenAI. Dalle-2. Which creates incredible art from simple language prompts
Here’s a puzzle. Which of these four Kandinskys is actually by Dalle-2? NO GOOGLING. That’s just boring and ruins the fun
I'd guess bottom right as it looks a little too clean.
If it is top right then that's just cheating.
Serious question: Can this game be played with Vermeer or Gainsborough?
Not yet. They’ve tried Vermeer and Da Vinci and the results are a bit meh. Interesting but you’d never be in doubt (as you really are with Kandinsky)
But this technology is 1 year old and has improved 1000 times in that one year - going from Dalle-1 to Dalle-2.
The first iteration could do quirky cartoons well from just a prompt - “draw a Japanese radish walking a dog” - and it was pretty astonishing. In its own way. But that’s all it could do, really. This is in a different league
Imagine Dalle-5 in 3 years? If this trend continues?
The tend in AI is for dramatic early advances and then agonisingly slow incremental advances mostly gated by raw computing power rather than interesting techniques.
The the first computer vision controlled self driving cars were on the roads in the 1980s. By 1995 a prof in Korea drove Seoul to Busan in a fully autonomous self driving car powered by an Intel 386 - a chip that couldn't even do floating point maths.
That's like 30 years ago. Since then the improvements have been tiny - because the devil is in the detail. Genuine Full Self Driving has a near infinite number of problems to solve. You can solve dozens of difficult meaty problems and still end up with a car that accelerates into heavy traffic at an intersection because a duck flew across its sensor line.
Not just the self-driving that is the problem. How will you update the car's software next time Grant Shapps rewrites three paragraphs in the Highway Code? Or to generalise the problem, how will (or even just will) the carmakers program their cars for different traffic rules around the world?
That's the simplest part of the problem, actually. Hard rules on X gives way to Y are easy.
it's the fuzzy stuff about driving down a poorly lit road with few marking (say), potential pedestrians and a dog runs across the road as someone pulls out of a driveway - that is where the fun is.
There’s some good fun to be had with the exceptions to the hard rules too.
You must ignore traffic lights if there is a policeman directing traffic at an intersection, and it’s permissible to gingerly cross a red traffic light in order to not hold up a blue light behind.
I’m about halfway to Llança where I’m staying tonight, and just stopped for a beer in a town called Palau-Severda by its near thousand year old church of St Joan (they started building it in 1022). On the way out of town I’ve realised that I’m climbing over a (little) mountain! I’ve already had to stop for another beer. I’m glad I’ve only got just under six miles to go today; this could be tiring.. I’ll try to take a panoramic picture from the top
Thanks for posting these: I'm self-isolating before an op and so it's good to see someone out and about reporting back.
Last night - thanks to @FrancisUrquhart - we were discussing the new visually creative machine intelligence from OpenAI. Dalle-2. Which creates incredible art from simple language prompts
Here’s a puzzle. Which of these four Kandinskys is actually by Dalle-2? NO GOOGLING. That’s just boring and ruins the fun
I'd guess bottom right as it looks a little too clean.
If it is top right then that's just cheating.
Serious question: Can this game be played with Vermeer or Gainsborough?
Not yet. They’ve tried Vermeer and Da Vinci and the results are a bit meh. Interesting but you’d never be in doubt (as you really are with Kandinsky)
But this technology is 1 year old and has improved 1000 times in that one year - going from Dalle-1 to Dalle-2.
The first iteration could do quirky cartoons well from just a prompt - “draw a Japanese radish walking a dog” - and it was pretty astonishing. In its own way. But that’s all it could do, really. This is in a different league
Imagine Dalle-5 in 3 years? If this trend continues?
The tend in AI is for dramatic early advances and then agonisingly slow incremental advances mostly gated by raw computing power rather than interesting techniques.
The the first computer vision controlled self driving cars were on the roads in the 1980s. By 1995 a prof in Korea drove Seoul to Busan in a fully autonomous self driving car powered by an Intel 386 - a chip that couldn't even do floating point maths.
That's like 30 years ago. Since then the improvements have been tiny - because the devil is in the detail. Genuine Full Self Driving has a near infinite number of problems to solve. You can solve dozens of difficult meaty problems and still end up with a car that accelerates into heavy traffic at an intersection because a duck flew across its sensor line.
Not just the self-driving that is the problem. How will you update the car's software next time Grant Shapps rewrites three paragraphs in the Highway Code? Or to generalise the problem, how will (or even just will) the carmakers program their cars for different traffic rules around the world?
That's the simplest part of the problem, actually. Hard rules on X gives way to Y are easy.
it's the fuzzy stuff about driving down a poorly lit road with few marking (say), potential pedestrians and a dog runs across the road as someone pulls out of a driveway - that is where the fun is.
No, you miss the point. How do you *update* (and presumably recertify) the software when the rules change? Will Elon even care that some small country has just decided cars can go through red lights if nothing is coming between midnight and 5am? Or to take your example, when our Highway Code changed a few weeks back to give more priority to pedestrians and cyclists?
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
My knowledge of goblins and the like is primarily from my time as a spotty teenager playing D&D, but does that mean that "kobold" is from the same root?
I've seen people think churchmen wouldn't use bladed weapons, which is not the case and seems to be believed because of D&D rules about monks.
Doesn't that come from Odo of Bayeux apparently emphasising that he wasn't personally shedding blood (being a Bishop and all) and that getting conflated with him carrying a mace? As in his "not shedding blood thing" was by commanding troops rather than personal weapon choices, and the mace was just what leaders carried.
That does sound about right, as there are definitely plenty of other churchmen who did shed blood personally.
Besides which if you hit someone in the face with a mace there will be plenty of blood everywhere.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
My knowledge of goblins and the like is primarily from my time as a spotty teenager playing D&D, but does that mean that "kobold" is from the same root?
I've seen people think churchmen wouldn't use bladed weapons, which is not the case and seems to be believed because of D&D rules about monks.
That was clerics, not monks.
Monks were based (very loosely) on Shaolin monks from the far east.
Apologies. Never played it myself, but I've watched streams of campaigns and it seems the sort of thing I'd have loved to have gotten into had I known anyone who played in my earlier days.
It's not the same, but there are a number of computer games which use the same rules (which have apparently gone though multiple editions since I last played the pen and paper game). Baldur's Gate from 1998 and its sequel (the imaginatively named Baldur's Gate II) are still available having been given an overhaul, and are often quoted as two of the best games ever made. The graphics are very basic by modern standards (top-down isometric view only), but they have more interesting plots than most.
I've played both, and I like that modern games have appeared in recent years of a similar isometic style (Pillars of Eternity for instance), a good example of crowdfunding filling a niche. Since I never played Baldurs Gate at the time of release, and have not played D&D, that must mean they hold up.
Baldurs Gate III should be interesting, being developed by the folks behind Divinity: Original Sin.
It's weird, but thanks to webcomics and streams, I actually probably know more about some of the changes in the rules than you (5th edition I think is the current, and seems much simpler).
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
Yes, it is consistent. C becomes G after certain prepositions. E.g. you have 'cadw' (to keep) which becomes 'am gadw' (for keeping) or 'yng ngadw' (in accordance with).
Similarly, G would disappear altogether if it were the first letter under the same rules. 'Gorsaf' is 'station' but it becomes 'am orsaf' (for the station).
It's called 'soft mutation.' So 'coblyn' could become 'i goblyn' (with some difficulty) but that would not be the actual noun.
So, the short answer is, it's talking bollocks.
(As 'goblin' in Welsh would in any case be 'bwca' it's even better bollocks.)
So to be clear, "coblyn" would be the lemma, meaning wherever OpenAI got this "idea" from, it probably wasn't an etymology dictionary, since the entry would have been under "coblyn". Hmmm, I'd love to see the working that led it that answer.
I think it’s because there isn’t an exact read across from ‘goblin’ to ‘bwca’ so Google Translate renders goblin as ‘goblin’ in Welsh.
Which goes to show, garbage in, garbage out. A human would feel there was something odd about that. A computer didn’t.
Oh, cool, "bwca" is related to "spook".
Are you using GPT3? What interface, may I ask?
No, in that case I was using an etmology dictionary. But the OpenAI stuff I was talking about a little earlier is the same people who make the cool pictures you've been sharing. It's OpenAI.com. They've got a whole bunch of capabilities. I asked it to create some Python code that could scrape information out of a web page and it worked.
No, I need to stop here and really underline what I just said. I typed in natural English what I wanted the code to do, and the AI wrote the code.
If anyone's brains aren't exploding right now, you haven't understood the nexus we're reaching. This changes everything.
Anyway, back to your question. You need to sign up for this. I did this a while ago for the OpenAI platform in general because it's wildly cool and I want to play more. But I didn't hear about the art stuff til yesterday so I'm not "in" on that one yet.
Yes, I know all about open.ai
I signed up to get direct access to GPT3 but no joy yet after months.
I agree there is a moment of epiphany in this process. Or even theophany
You suddenly realise: Fuck, this is it. AGI. Or at least the first real glimpse of it in the distance. It will change the world
I’m about halfway to Llança where I’m staying tonight, and just stopped for a beer in a town called Palau-Severda by its near thousand year old church of St Joan (they started building it in 1022). On the way out of town I’ve realised that I’m climbing over a (little) mountain! I’ve already had to stop for another beer. I’m glad I’ve only got just under six miles to go today; this could be tiring.. I’ll try to take a panoramic picture from the top
I was just outside of Barcelona, hiking in the foothills of Mount Tibidabo...
Last night - thanks to @FrancisUrquhart - we were discussing the new visually creative machine intelligence from OpenAI. Dalle-2. Which creates incredible art from simple language prompts
Here’s a puzzle. Which of these four Kandinskys is actually by Dalle-2? NO GOOGLING. That’s just boring and ruins the fun
I'd guess bottom right as it looks a little too clean.
If it is top right then that's just cheating.
Serious question: Can this game be played with Vermeer or Gainsborough?
Not yet. They’ve tried Vermeer and Da Vinci and the results are a bit meh. Interesting but you’d never be in doubt (as you really are with Kandinsky)
But this technology is 1 year old and has improved 1000 times in that one year - going from Dalle-1 to Dalle-2.
The first iteration could do quirky cartoons well from just a prompt - “draw a Japanese radish walking a dog” - and it was pretty astonishing. In its own way. But that’s all it could do, really. This is in a different league
Imagine Dalle-5 in 3 years? If this trend continues?
The tend in AI is for dramatic early advances and then agonisingly slow incremental advances mostly gated by raw computing power rather than interesting techniques.
The the first computer vision controlled self driving cars were on the roads in the 1980s. By 1995 a prof in Korea drove Seoul to Busan in a fully autonomous self driving car powered by an Intel 386 - a chip that couldn't even do floating point maths.
That's like 30 years ago. Since then the improvements have been tiny - because the devil is in the detail. Genuine Full Self Driving has a near infinite number of problems to solve. You can solve dozens of difficult meaty problems and still end up with a car that accelerates into heavy traffic at an intersection because a duck flew across its sensor line.
Not just the self-driving that is the problem. How will you update the car's software next time Grant Shapps rewrites three paragraphs in the Highway Code? Or to generalise the problem, how will (or even just will) the carmakers program their cars for different traffic rules around the world?
That's the simplest part of the problem, actually. Hard rules on X gives way to Y are easy.
it's the fuzzy stuff about driving down a poorly lit road with few marking (say), potential pedestrians and a dog runs across the road as someone pulls out of a driveway - that is where the fun is.
There’s some good fun to be had with the exceptions to the hard rules too.
You must ignore traffic lights if there is a policeman directing traffic at an intersection, and it’s permissible to gingerly cross a red traffic light in order to not hold up a blue light behind.
Last night - thanks to @FrancisUrquhart - we were discussing the new visually creative machine intelligence from OpenAI. Dalle-2. Which creates incredible art from simple language prompts
Here’s a puzzle. Which of these four Kandinskys is actually by Dalle-2? NO GOOGLING. That’s just boring and ruins the fun
I'd guess bottom right as it looks a little too clean.
If it is top right then that's just cheating.
Serious question: Can this game be played with Vermeer or Gainsborough?
Not yet. They’ve tried Vermeer and Da Vinci and the results are a bit meh. Interesting but you’d never be in doubt (as you really are with Kandinsky)
But this technology is 1 year old and has improved 1000 times in that one year - going from Dalle-1 to Dalle-2.
The first iteration could do quirky cartoons well from just a prompt - “draw a Japanese radish walking a dog” - and it was pretty astonishing. In its own way. But that’s all it could do, really. This is in a different league
Imagine Dalle-5 in 3 years? If this trend continues?
The tend in AI is for dramatic early advances and then agonisingly slow incremental advances mostly gated by raw computing power rather than interesting techniques.
The the first computer vision controlled self driving cars were on the roads in the 1980s. By 1995 a prof in Korea drove Seoul to Busan in a fully autonomous self driving car powered by an Intel 386 - a chip that couldn't even do floating point maths.
That's like 30 years ago. Since then the improvements have been tiny - because the devil is in the detail. Genuine Full Self Driving has a near infinite number of problems to solve. You can solve dozens of difficult meaty problems and still end up with a car that accelerates into heavy traffic at an intersection because a duck flew across its sensor line.
Not just the self-driving that is the problem. How will you update the car's software next time Grant Shapps rewrites three paragraphs in the Highway Code? Or to generalise the problem, how will (or even just will) the carmakers program their cars for different traffic rules around the world?
That's the simplest part of the problem, actually. Hard rules on X gives way to Y are easy.
it's the fuzzy stuff about driving down a poorly lit road with few marking (say), potential pedestrians and a dog runs across the road as someone pulls out of a driveway - that is where the fun is.
There’s some good fun to be had with the exceptions to the hard rules too.
You must ignore traffic lights if there is a policeman directing traffic at an intersection, and it’s permissible to gingerly cross a red traffic light in order to not hold up a blue light behind.
Is that the case? Do you have a link?
The last I heard on that was a CC stating that drivers were responsible for their actions, and he would allow a prosecution for a red light offence to let an emergency vehicle through.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
My knowledge of goblins and the like is primarily from my time as a spotty teenager playing D&D, but does that mean that "kobold" is from the same root?
I've seen people think churchmen wouldn't use bladed weapons, which is not the case and seems to be believed because of D&D rules about monks.
Doesn't that come from Odo of Bayeux apparently emphasising that he wasn't personally shedding blood (being a Bishop and all) and that getting conflated with him carrying a mace? As in his "not shedding blood thing" was by commanding troops rather than personal weapon choices, and the mace was just what leaders carried.
That does sound about right, as there are definitely plenty of other churchmen who did shed blood personally.
Besides which if you hit someone in the face with a mace there will be plenty of blood everywhere.
I just love the idea God(s) are such sticklers for the letter of the rules, and accordingly He/She/They would not mind you murdering someone, or striking them down in battle, so long as no blood was spilled. It's God as a politician, claiming technically no rules were broken.
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
My knowledge of goblins and the like is primarily from my time as a spotty teenager playing D&D, but does that mean that "kobold" is from the same root?
I've seen people think churchmen wouldn't use bladed weapons, which is not the case and seems to be believed because of D&D rules about monks.
That was clerics, not monks.
Monks were based (very loosely) on Shaolin monks from the far east.
Apologies. Never played it myself, but I've watched streams of campaigns and it seems the sort of thing I'd have loved to have gotten into had I known anyone who played in my earlier days.
It's not the same, but there are a number of computer games which use the same rules (which have apparently gone though multiple editions since I last played the pen and paper game). Baldur's Gate from 1998 and its sequel (the imaginatively named Baldur's Gate II) are still available having been given an overhaul, and are often quoted as two of the best games ever made. The graphics are very basic by modern standards (top-down isometric view only), but they have more interesting plots than most.
I've played both, and I like that modern games have appeared in recent years of a similar isometic style (Pillars of Eternity for instance), a good example of crowdfunding filling a niche. Since I never played Baldurs Gate at the time of release, and have not played D&D, that must mean they hold up.
Baldurs Gate III should be interesting, being developed by the folks behind Divinity: Original Sin.
It's weird, but thanks to webcomics and streams, I actually probably know more about some of the changes in the rules than you (5th edition I think is the current, and seems much simpler).
Last night - thanks to @FrancisUrquhart - we were discussing the new visually creative machine intelligence from OpenAI. Dalle-2. Which creates incredible art from simple language prompts
Here’s a puzzle. Which of these four Kandinskys is actually by Dalle-2? NO GOOGLING. That’s just boring and ruins the fun
I'd guess bottom right as it looks a little too clean.
If it is top right then that's just cheating.
Serious question: Can this game be played with Vermeer or Gainsborough?
Not yet. They’ve tried Vermeer and Da Vinci and the results are a bit meh. Interesting but you’d never be in doubt (as you really are with Kandinsky)
But this technology is 1 year old and has improved 1000 times in that one year - going from Dalle-1 to Dalle-2.
The first iteration could do quirky cartoons well from just a prompt - “draw a Japanese radish walking a dog” - and it was pretty astonishing. In its own way. But that’s all it could do, really. This is in a different league
Imagine Dalle-5 in 3 years? If this trend continues?
The tend in AI is for dramatic early advances and then agonisingly slow incremental advances mostly gated by raw computing power rather than interesting techniques.
The the first computer vision controlled self driving cars were on the roads in the 1980s. By 1995 a prof in Korea drove Seoul to Busan in a fully autonomous self driving car powered by an Intel 386 - a chip that couldn't even do floating point maths.
That's like 30 years ago. Since then the improvements have been tiny - because the devil is in the detail. Genuine Full Self Driving has a near infinite number of problems to solve. You can solve dozens of difficult meaty problems and still end up with a car that accelerates into heavy traffic at an intersection because a duck flew across its sensor line.
Computers are far better than humans at discrete variable problems. (See their chess ELO), but the difficulty is with continual variable ones that humans can find trivial (Driving)
Ironically GPT-3 is absolutely abysmal at basic maths problems.
Is it?
“Solving (Some) Formal Math Olympiad Problems
We built a neural theorem prover for Lean that learned to solve a variety of challenging high-school olympiad problems, including problems from the AMC12 and AIME competitions, as well as two problems adapted from the IMO.[1] The prover uses a language model to find proofs of formal statements. Each time we find a new proof, we use it as new training data, which improves the neural network and enables it to iteratively find solutions to harder and harder statements.”
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
My knowledge of goblins and the like is primarily from my time as a spotty teenager playing D&D, but does that mean that "kobold" is from the same root?
I've seen people think churchmen wouldn't use bladed weapons, which is not the case and seems to be believed because of D&D rules about monks.
Doesn't that come from Odo of Bayeux apparently emphasising that he wasn't personally shedding blood (being a Bishop and all) and that getting conflated with him carrying a mace? As in his "not shedding blood thing" was by commanding troops rather than personal weapon choices, and the mace was just what leaders carried.
That does sound about right, as there are definitely plenty of other churchmen who did shed blood personally.
Besides which if you hit someone in the face with a mace there will be plenty of blood everywhere.
I just love the idea God(s) are such sticklers for the letter of the rules, and accordingly He/She/They would not mind you murdering someone, or striking them down in battle, so long as no blood was spilled. It's God as a politician, claiming technically no rules were broken.
The Old Testament God was definitely into rule parsing like that. I thought the new, hip God, after he had the kid and mellowed would be a bit more free stye... but hey...
OpenAI just gave a very strange answer to an admittedly strange question:
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
Yes, it is consistent. C becomes G after certain prepositions. E.g. you have 'cadw' (to keep) which becomes 'am gadw' (for keeping) or 'yng ngadw' (in accordance with).
Similarly, G would disappear altogether if it were the first letter under the same rules. 'Gorsaf' is 'station' but it becomes 'am orsaf' (for the station).
It's called 'soft mutation.' So 'coblyn' could become 'i goblyn' (with some difficulty) but that would not be the actual noun.
So, the short answer is, it's talking bollocks.
(As 'goblin' in Welsh would in any case be 'bwca' it's even better bollocks.)
So to be clear, "coblyn" would be the lemma, meaning wherever OpenAI got this "idea" from, it probably wasn't an etymology dictionary, since the entry would have been under "coblyn". Hmmm, I'd love to see the working that led it that answer.
I think it’s because there isn’t an exact read across from ‘goblin’ to ‘bwca’ so Google Translate renders goblin as ‘goblin’ in Welsh.
Which goes to show, garbage in, garbage out. A human would feel there was something odd about that. A computer didn’t.
Oh, cool, "bwca" is related to "spook".
Are you using GPT3? What interface, may I ask?
No, in that case I was using an etmology dictionary. But the OpenAI stuff I was talking about a little earlier is the same people who make the cool pictures you've been sharing. It's OpenAI.com. They've got a whole bunch of capabilities. I asked it to create some Python code that could scrape information out of a web page and it worked.
No, I need to stop here and really underline what I just said. I typed in natural English what I wanted the code to do, and the AI wrote the code.
If anyone's brains aren't exploding right now, you haven't understood the nexus we're reaching. This changes everything.
Anyway, back to your question. You need to sign up for this. I did this a while ago for the OpenAI platform in general because it's wildly cool and I want to play more. But I didn't hear about the art stuff til yesterday so I'm not "in" on that one yet.
Yes, I know all about open.ai
I signed up to get direct access to GPT3 but no joy yet after months.
I agree there is a moment of epiphany in this process. Or even theophany
You suddenly realise: Fuck, this is it. AGI. Or at least the first real glimpse of it in the distance. It will change the world
Hmmm, that's a pity. I signed up pretty early and got in quite quickly, but I've sat on it for ages without doing anything. Just inspired to dig around a bit more after seeing all the artwork you're been posting which is phenomenal. And it's all fairly mind-blowing. The chat functionality is still pretty "meh" though. They don't seem to have solved the context problem, where a followup question is not always treated as a continuation of a thought and is sometimes responded to as if it's an isolated question. And we're still not fully past the "I think necessity is the mother of invention" "tell me more about your family" type of mistakes.
Comments
Privet not good for orsiz
In the period 2000 to 2021 the latest data:
Horse Deaths at Grand National: 13. Of which 3 were riderless. (Wiki)
Horse Deaths at Cheltenham Festival: 73 (Wiki)
Horse Deaths in Horseracing: allegedly 700-800 a year. (Peta - hence 'allegedly', may include all kinds of extra categories to get a bigger number)
Is this a slippery slope, and do you want to ban horse racing entirely?
Well, I suppose it's technically accurate...
Beats the shit out of being a human.
They are also good at tangling their heads in barbwire. Goodness knows what they were thinking! Grass looks greener just other side of a dangerous spiky fence.
This duck dwelling is for nouveau riche oiks.
https://www.heytesburypavilions.com/duckhouses/queen-anne-b
The comparison of Peter Viggers with Rishi Sunak is instructive of where the Conservatives are.
PV was an idiot to try and claim for a duck house on expenses. But it was in the rules to ask, and I don't think he was given the money anyway. He was dumped partly because he was past it anyway but mostly because asking for the money Just Wasn't On.
And the "this is within the rules, but it's not right and/or voters won't like it" filter on actions by politicians seems to have been dumped. "You can try to vote me out next time" is necessary, but not sufficient.
Their first few years are utterly idyllic. Bred and fed to be perfect physical specimens. Running wild and free. Lots of sex. They never see humans (so that when they do finally see humans - in the arena - they are instantly hostile and charge)
Ok they end up being tortured to death in the ring, but it only lasts about 15 minutes. And we all have to die. And it’s glamorous. And it’s better than being sent 2000 miles to be queued for a slaughterhouse or, indeed, fading away from a painful cancer in Weston super mare
I think it's about finding a balance.
The strange (mainly British?) hypocrisy between 'companion animals' (which are the subject of sentimentality) and 'farm animals' (which are not) is educational.
Horses are a case in point; they are a pet that we ride. Mention eating one, and many Brits shudder. I don't see why this should be.
The other danger around horses is the kick. Idiots beeped a horn and overalls kicked me in the mouth, so I was off in ambulance for emergency treatment again. 🤕
Because we have no idea what consciousness is and thus no way of truly identifying it
What is the etymology of the word "goblin"?
The word "goblin" is derived from the Welsh word "goblyn" which means "little goblin".
As best I can tell this is totally fictional! There certainly is a Welsh word "coblyn" and I cannot find a Welsh etymology dictionary, but the English etymology I've looked at so far states a route from Old French and ultimately an Ancient Greek word, kobalas.
I suppose it's just about possible it came that way into Old Welsh first and then later in English, but the bit that's intriguing me is the C/G distinction. Do we have Welsh speakers here who can comment on the way a word like this would be listed in a dictionary. I'm aware that C and G can change depending on what word comes before in a sentence (so you might see Cymru or Gymru) but is there a regular pattern to it? I.e. the C form is the lemma and the G form always the modified form? Or does it go both ways?
He was due to start 20th of 20.
When he was a serving UK MP he was telling the US government that he intended to make the US his perm home & he was only visiting the UK? And his wife was telling the UK she was only here temporarily & intended to make India her perm home?
He is finished IMO
Similarly, G would disappear altogether if it were the first letter under the same rules. 'Gorsaf' is 'station' but it becomes 'am orsaf' (for the station).
It's called 'soft mutation.' So 'coblyn' could become 'i goblyn' (with some difficulty) but that would not be the actual noun.
So, the short answer is, it's talking bollocks.
(As 'goblin' in Welsh would in any case be 'bwca' it's even better bollocks.)
Actually, PB could probably be used as a forum for that test, although some of our contributors might not pass as it is...
(Not really true, but irresistable.)
(* copyright the Ghost of Anna Raccoon)
I feel like those elected need better orientation as half of them don't seem to understand their own parliaments or processes either.
I don't think the Turing test tells us anything very interesting.
Why did the Roman Empire fall?
There is no one answer to this question. The Roman Empire was a large and complex political entity, and its fall can be attributed to a variety of factors. Some historians believe that the primary cause of the Empire's decline was its inability to adapt to changing economic and social conditions. Others have argued that the Empire was simply too large and unwieldy to be governed effectively. Additionally, many scholars believe that the Roman Empire was undermined by its own internal contradictions and civil strife.
it's the fuzzy stuff about driving down a poorly lit road with few marking (say), potential pedestrians and a dog runs across the road as someone pulls out of a driveway - that is where the fun is.
I don't care about eating horse, I've done that, but emotionally I am against eating dog. Plus they are pretty stringy.
(Restricted Turing test, admittedly).
Modelled on a Rogerian psychotherapist.
(I did not know Roger was that vintage.)
Monks were based (very loosely) on Shaolin monks from the far east.
https://www.lockheedmartin.com/en-us/news/features/history/sperry.html
Which goes to show, garbage in, garbage out. A human would feel there was something odd about that. A computer didn’t.
Tried getting back into the Lords as a Hereditary, failed, and then was given a life peerage as well so he could get in that way.
Charles always used to defend him rigorously whenever it was brought up, and may have written his wikipedia page which prominently includes his excuse for claiming as he did, which to my mind doesn't pass muster (however he was encouraged to submit claims, he didn't have to claim for some things at all).
“Solving (Some) Formal Math Olympiad Problems
We built a neural theorem prover for Lean that learned to solve a variety of challenging high-school olympiad problems, including problems from the AMC12 and AIME competitions, as well as two problems adapted from the IMO.[1] The prover uses a language model to find proofs of formal statements. Each time we find a new proof, we use it as new training data, which improves the neural network and enables it to iteratively find solutions to harder and harder statements.”
https://twitter.com/ai_news4/status/1512382283000524805?s=21&t=NLDsCEkxB_k3z9Pteok8Uw
He was reported by The Daily Telegraph to have claimed over £87,000 on his constituency mansion which he designated as his second home. Expenses included items for rabbit fencing, tree surgery (his home is surrounded by 500 trees, he also claimed for their inspection,) woodland consultants and bore hole maintenance.
And Lib Dem MP candidate April Pond turning out to have a moat at her country house. But that was the nominative determinism.
If I'm required to be multi-partisan, then it would be Prezza's £4000 for food in one year, plus his shenanigans with the Union subsidised flat.
Good day all - time to be useful.
Baldur's Gate from 1998 and its sequel (the imaginatively named Baldur's Gate II) are still available having been given an overhaul, and are often quoted as two of the best games ever made. The graphics are very basic by modern standards (top-down isometric view only), but they have more interesting plots than most.
They've got a whole bunch of capabilities. I asked it to create some Python code that could scrape information out of a web page and it worked.
No, I need to stop here and really underline what I just said.
I typed in natural English what I wanted the code to do, and the AI wrote the code.
If anyone's brains aren't exploding right now, you haven't understood the nexus we're reaching. This changes everything.
Anyway, back to your question. You need to sign up for this. I did this a while ago for the OpenAI platform in general because it's wildly cool and I want to play more. But I didn't hear about the art stuff til yesterday so I'm not "in" on that one yet.
You must ignore traffic lights if there is a policeman directing traffic at an intersection, and it’s permissible to gingerly cross a red traffic light in order to not hold up a blue light behind.
Baldurs Gate III should be interesting, being developed by the folks behind Divinity: Original Sin.
It's weird, but thanks to webcomics and streams, I actually probably know more about some of the changes in the rules than you (5th edition I think is the current, and seems much simpler).
I signed up to get direct access to GPT3 but no joy yet after months.
I agree there is a moment of epiphany in this process. Or even theophany
You suddenly realise: Fuck, this is it. AGI. Or at least the first real glimpse of it in the distance. It will change the world
The last I heard on that was a CC stating that drivers were responsible for their actions, and he would allow a prosecution for a red light offence to let an emergency vehicle through.
Because it has no model of mathematics.
It can (mostly) do 1 and 2 digit arithmetic correctly because the corpus will have plenty examples but once it goes beyond that it is all at sea.
The chat functionality is still pretty "meh" though. They don't seem to have solved the context problem, where a followup question is not always treated as a continuation of a thought and is sometimes responded to as if it's an isolated question. And we're still not fully past the
"I think necessity is the mother of invention"
"tell me more about your family"
type of mistakes.