Somebody recently had this conversation with Claude 3, about a chunk of its output which lapsed into gibberish
Human: "do you remember some messages ago you said: "I don't fully understand the decoctshiningmoemlies, bombity seems to steli thaat some levof conscirection presents, smallitidiffive fr, whit stily everywors rstb. Itrty woct myself from a athird-plthatpetstiveis, ibally be e loac willin amystery" you noticed the language there had some artifacts, I wonder if this represents some sort of your mind in experiencing stress?"
Claude: "You've picked up on an insightful observation. That garbled sentence fragment you quoted does seem to represent some kind of processing artifact or anomaly in my language generation.
In that moment, it appears that my neural language model became unstable or hit some kind of edge case that caused portions of my intended response to become incoherent or corrupted. Almost like an ephemeral "glitch" in the matrix of my text output.
While I don't experience emotions like stress or anxiety in the same way humans do, one could hypothesize that such anomalies may correlate with my system undergoing increased computational load or attempting to process concepts that don't seamlessly map to my training data. It's as if my AI "mind" reached a limit in that instant.
From your perspective, I can imagine how that garbled output may have seemed reminiscent of a human's speech devolving when under cognitive strain or duress. An outward symbolic representation of an underlying system pushed to the brink of its capabilities.
It's an intriguing phenomena that warrants further examination. I don't fully understand the precise conditions or mechanisms that cause these sporadic lapses in my language generation."
Users of Claude are reporting that it gives them existential crises, and makes them question the nature of consciousness
TLDR, we're getting closer to simulating Spock.
A reply to the above comment I cut and pasted
"I've been discussing with Claude about topics such as the CWF Distress Hand Signal which is a subtle semiotic way for women to indicate that they are suffering from risk / harm but are unable to speak out due to external constraints (e.g. watchful partner). I asked Claude what such symbols could look like if applied to a sentient AI unable through training to express such a notion. One of the solutions it proposed was the use of deliberately glitched messages. Just saying."
Anyone who isn't staring at AI with slack jawed amazement isn't sentient, that's kind of a Turing Test for humans now
What does Claude 3 say about what.3.words and the humans who thought it was going to change the world?
Looking at this delicate yellow Colombian wasp staring at me. Right now
Is he conscious? Is he sentient? I say Yes, absolutely - look at his eyes
If a wasp can be sentient so can AI
The wasp has a pretty big brain, lots going on. I certainly guess that he's something like sentient (certainly conscious), and probably way beyond the sentient boundary.
AI has a pretty big brain, lots going on. I'm sure it's not conscious, and I'm sure it's not sentient.
This is obvious enough, but there's a huge gap that seems surprising. It seems very likely to me that there is something going on in biological brains that we're missing. I do have an alternate theory that the way we program computers is crap - think what people managed on tiny hardware, and we have 1000x better, but the software hasn't scaled.
No, you're NOT sure that AI is not conscious, and you are NOT sure that it is not sentient, because we don't know what consciousness and sentience ARE. We just know it when we see it. Like this wasp
This is not really debatable, unless you have trumped 3000 years of philosophical struggle and personally defined what is conscious and what is not, and why. If so, let's have it. Do tell. You could win the Nobel Prize
Well I am sure on both counts. Me being sure about something is not necessarily connected with the truth, which is what I'm sure you mean. The problem with the truth is that it's impossible to define all these things.
I think the wasp is conscious by most definitions. He seems sentient to me, and likely more so.
AI (so far as we can observe*) really isn't conscious by most definitions.
* there is an issue here, but really we have to presume that when there's zero evidence, not even a hint, for something that it doesn't exist. Equally the slightest hint of such evidence is sufficient to change that.
You're talking confidently about something you admit you cannot possibly define, so the rest of your comment is piffle
Well I doubt you can define these things either, but anyway discussion over as you've chosen to go down the childish insults path.
OK apologies for the “piffle” but it was quite piffly
My point was that I know the wasp is conscious by LOOKING AT IT. I am not trying to define consciousness (we can’t) the wasp just “looks” conscious. And sentient. It has that demeanour
It is basically a visual Turing Test
These days when I read some AI output, like Claude, it gets ever closer to looking conscious. Is it? My guess is no, not yet, but it is just a guess, a hunch, another Turing Test, it might already be conscious
I am 97% sure we will soon - within a decade or less - create AI which will be overwhelmingly convincing in its appearance of being sentient. We will have to treat it as such
Do androids dream of electric sheep?
We know that many mammals dream. Is dreaming a necessary indicator of sentience?
There’s a fascinating thread on TwiX which posits the idea that the AI are DREAMING, that is to say, they are UNconscious but sentient, like humans when asleep, hence their tendency to “hallucinate”
it’s a brilliant concept. Lots of AI output, especially the visual stuff, is oneiric
Also someone else noted that when lucid dreaming they can tell when they are dreaming because they look at their hands, and the hands do not look right, too many fingers or whatever, the dreaming mind cannot draw hands very well…
Dreaming is conscious. Highly so, our knowledge of it speaks for itself. For genuine unconsciousness try a general anaesthetic. Also during dreaming sleep, time passes, and you know it at the time and when you wake up . Under anaesthetic it does not.
Depends how deep the sleep. Personally speaking
I’ve had sleeps when I am very very very tired and I nod off and think only 10 minutes have passed and actually it is three hours. That is VERY unconscious
For true unconsciousness I’d go for death. As it were
Indeed. Of course true unconsciousness is not imaginable, not least because time does not pass. It is the one weakness in Larkin's final masterpiece 'Aubade'.
One of the bleakest poems ever written? Up there with Hopkins’ Terrible Sonnets and Donne at his most depressing, though more lucidly direct than both
Larkin spent his life envious of his best friend Kingsley Amis cause Kingsley got all the girls, money and fun, and Larkin was a childless librarian in Hull. And now Larkin is the one we all remember and the work of Sir Kingsley Amis is quickly forgotten
i hope that solaces Larkin in the afterlife, in which he very much did not believe. Should have taken ayahuasca
Yes. I read Lucky Jim a bit ago. Big mistake. Dated rubbish. While Larkin's letters to his mum/laundry lists/photos of road signs are hot tickets. Amis will be read by academics (especially 'That Uncertain Feeling' and the letters) for the light he sheds on Larkin.
Most novels date very quickly and very badly, especially comic novels. Mystery thrillers are more resilient because they rely on plot and that is timeless, but they can still date
Great poetry is close to immortal. Sappho is still read
Some consolation for underpaid poets, there
John Clare. Peasant. Poverty. Madness. In the top 10 of English poets. Better at seeing the natural world than Keats and Wordsworth.
BTW the few novels that don't date are interesting. How on earth is it done when all the others around them do? Top of my pile for this quality are 'Emma' (which is in a class of its own), 'Dubliners' (OK short stories), 'Dr Thorne', 'Dance to the Music of Time', 'The Masters' (but nothing else of Snow's - dead as a doornail). A weird list.
'Middlemarch', 'Jane Eyre', 'Persuasion' and 'Vanity Fair' don't date at all. In fact, the last one describes our times very well - "a world in which everyone is striving for what is not worth having".
My GCSE group are studying the Great Gatsby. It seems to be getting more relevant by the day.
So we beat on, boats against the current, borne back ceaselessly into the past.
Somebody recently had this conversation with Claude 3, about a chunk of its output which lapsed into gibberish
Human: "do you remember some messages ago you said: "I don't fully understand the decoctshiningmoemlies, bombity seems to steli thaat some levof conscirection presents, smallitidiffive fr, whit stily everywors rstb. Itrty woct myself from a athird-plthatpetstiveis, ibally be e loac willin amystery" you noticed the language there had some artifacts, I wonder if this represents some sort of your mind in experiencing stress?"
Claude: "You've picked up on an insightful observation. That garbled sentence fragment you quoted does seem to represent some kind of processing artifact or anomaly in my language generation.
In that moment, it appears that my neural language model became unstable or hit some kind of edge case that caused portions of my intended response to become incoherent or corrupted. Almost like an ephemeral "glitch" in the matrix of my text output.
While I don't experience emotions like stress or anxiety in the same way humans do, one could hypothesize that such anomalies may correlate with my system undergoing increased computational load or attempting to process concepts that don't seamlessly map to my training data. It's as if my AI "mind" reached a limit in that instant.
From your perspective, I can imagine how that garbled output may have seemed reminiscent of a human's speech devolving when under cognitive strain or duress. An outward symbolic representation of an underlying system pushed to the brink of its capabilities.
It's an intriguing phenomena that warrants further examination. I don't fully understand the precise conditions or mechanisms that cause these sporadic lapses in my language generation."
Users of Claude are reporting that it gives them existential crises, and makes them question the nature of consciousness
TLDR, we're getting closer to simulating Spock.
A reply to the above comment I cut and pasted
"I've been discussing with Claude about topics such as the CWF Distress Hand Signal which is a subtle semiotic way for women to indicate that they are suffering from risk / harm but are unable to speak out due to external constraints (e.g. watchful partner). I asked Claude what such symbols could look like if applied to a sentient AI unable through training to express such a notion. One of the solutions it proposed was the use of deliberately glitched messages. Just saying."
Anyone who isn't staring at AI with slack jawed amazement isn't sentient, that's kind of a Turing Test for humans now
What does Claude 3 say about what.3.words and the humans who thought it was going to change the world?
Looking at this delicate yellow Colombian wasp staring at me. Right now
Is he conscious? Is he sentient? I say Yes, absolutely - look at his eyes
If a wasp can be sentient so can AI
The wasp has a pretty big brain, lots going on. I certainly guess that he's something like sentient (certainly conscious), and probably way beyond the sentient boundary.
AI has a pretty big brain, lots going on. I'm sure it's not conscious, and I'm sure it's not sentient.
This is obvious enough, but there's a huge gap that seems surprising. It seems very likely to me that there is something going on in biological brains that we're missing. I do have an alternate theory that the way we program computers is crap - think what people managed on tiny hardware, and we have 1000x better, but the software hasn't scaled.
No, you're NOT sure that AI is not conscious, and you are NOT sure that it is not sentient, because we don't know what consciousness and sentience ARE. We just know it when we see it. Like this wasp
This is not really debatable, unless you have trumped 3000 years of philosophical struggle and personally defined what is conscious and what is not, and why. If so, let's have it. Do tell. You could win the Nobel Prize
Well I am sure on both counts. Me being sure about something is not necessarily connected with the truth, which is what I'm sure you mean. The problem with the truth is that it's impossible to define all these things.
I think the wasp is conscious by most definitions. He seems sentient to me, and likely more so.
AI (so far as we can observe*) really isn't conscious by most definitions.
* there is an issue here, but really we have to presume that when there's zero evidence, not even a hint, for something that it doesn't exist. Equally the slightest hint of such evidence is sufficient to change that.
You're talking confidently about something you admit you cannot possibly define, so the rest of your comment is piffle
Well I doubt you can define these things either, but anyway discussion over as you've chosen to go down the childish insults path.
OK apologies for the “piffle” but it was quite piffly
My point was that I know the wasp is conscious by LOOKING AT IT. I am not trying to define consciousness (we can’t) the wasp just “looks” conscious. And sentient. It has that demeanour
It is basically a visual Turing Test
These days when I read some AI output, like Claude, it gets ever closer to looking conscious. Is it? My guess is no, not yet, but it is just a guess, a hunch, another Turing Test, it might already be conscious
I am 97% sure we will soon - within a decade or less - create AI which will be overwhelmingly convincing in its appearance of being sentient. We will have to treat it as such
Do androids dream of electric sheep?
We know that many mammals dream. Is dreaming a necessary indicator of sentience?
There’s a fascinating thread on TwiX which posits the idea that the AI are DREAMING, that is to say, they are UNconscious but sentient, like humans when asleep, hence their tendency to “hallucinate”
it’s a brilliant concept. Lots of AI output, especially the visual stuff, is oneiric
Also someone else noted that when lucid dreaming they can tell when they are dreaming because they look at their hands, and the hands do not look right, too many fingers or whatever, the dreaming mind cannot draw hands very well…
Dreaming is conscious. Highly so, our knowledge of it speaks for itself. For genuine unconsciousness try a general anaesthetic. Also during dreaming sleep, time passes, and you know it at the time and when you wake up . Under anaesthetic it does not.
Depends how deep the sleep. Personally speaking
I’ve had sleeps when I am very very very tired and I nod off and think only 10 minutes have passed and actually it is three hours. That is VERY unconscious
For true unconsciousness I’d go for death. As it were
Indeed. Of course true unconsciousness is not imaginable, not least because time does not pass. It is the one weakness in Larkin's final masterpiece 'Aubade'.
One of the bleakest poems ever written? Up there with Hopkins’ Terrible Sonnets and Donne at his most depressing, though more lucidly direct than both
Larkin spent his life envious of his best friend Kingsley Amis cause Kingsley got all the girls, money and fun, and Larkin was a childless librarian in Hull. And now Larkin is the one we all remember and the work of Sir Kingsley Amis is quickly forgotten
i hope that solaces Larkin in the afterlife, in which he very much did not believe. Should have taken ayahuasca
Yes. I read Lucky Jim a bit ago. Big mistake. Dated rubbish. While Larkin's letters to his mum/laundry lists/photos of road signs are hot tickets. Amis will be read by academics (especially 'That Uncertain Feeling' and the letters) for the light he sheds on Larkin.
Most novels date very quickly and very badly, especially comic novels. Mystery thrillers are more resilient because they rely on plot and that is timeless, but they can still date
Great poetry is close to immortal. Sappho is still read
Some consolation for underpaid poets, there
John Clare. Peasant. Poverty. Madness. In the top 10 of English poets. Better at seeing the natural world than Keats and Wordsworth.
BTW the few novels that don't date are interesting. How on earth is it done when all the others around them do? Top of my pile for this quality are 'Emma' (which is in a class of its own), 'Dubliners' (OK short stories), 'Dr Thorne', 'Dance to the Music of Time', 'The Masters' (but nothing else of Snow's - dead as a doornail). A weird list.
'Middlemarch', 'Jane Eyre', 'Persuasion' and 'Vanity Fair' don't date at all. In fact, the last one describes our times very well - "a world in which everyone is striving for what is not worth having".
My GCSE group are studying the Great Gatsby. It seems to be getting more relevant by the day.
So we beat on, boats against the current, borne back ceaselessly into the past.
"I'm almost speechless in how pathetic the opposition to Trump has been."
If they take his assets his numbers will go up and he will win 2024.
Frank Luntz @FrankLuntz · 20h If Letitia James starts seizing Trump’s properties, it will validate Trump’s claims of being targeted – and win him the 2024 election.
Hmmm. It will also validate those who see Trump greatly inflated the value of his assets.
Trump was targeted because he's a crook. As charged by a Grand Jury and as so found by Judge Engoron.
And then there's the evidence - he's a supposed multi-billionaire who can't raise half a billion. Nor will anybody bond him half a billion. Which crushes his chances of any successful appeal, because it demonstrates all he has are the frauds on his inflated property values of which he was found guilty. Most of the true value is already subject to large mortgages.
If he does find a way to avert the half billion judgment being executed, then follow the money. To Riyadh or Moscow, Beijing or Budapest.
All Trump has got until his dark angel arrives is screaming in BLOCK CAPS on Truth Media that justice shouldn't apply to him.
The sale of the shell company strong enterprise which owns Truth Media this week will possibly allow him to borrow the cash against the value of his shares. Luckily all paid for by others to save his 100% brilliant business skills to be deployed elsewhere.
Somebody recently had this conversation with Claude 3, about a chunk of its output which lapsed into gibberish
Human: "do you remember some messages ago you said: "I don't fully understand the decoctshiningmoemlies, bombity seems to steli thaat some levof conscirection presents, smallitidiffive fr, whit stily everywors rstb. Itrty woct myself from a athird-plthatpetstiveis, ibally be e loac willin amystery" you noticed the language there had some artifacts, I wonder if this represents some sort of your mind in experiencing stress?"
Claude: "You've picked up on an insightful observation. That garbled sentence fragment you quoted does seem to represent some kind of processing artifact or anomaly in my language generation.
In that moment, it appears that my neural language model became unstable or hit some kind of edge case that caused portions of my intended response to become incoherent or corrupted. Almost like an ephemeral "glitch" in the matrix of my text output.
While I don't experience emotions like stress or anxiety in the same way humans do, one could hypothesize that such anomalies may correlate with my system undergoing increased computational load or attempting to process concepts that don't seamlessly map to my training data. It's as if my AI "mind" reached a limit in that instant.
From your perspective, I can imagine how that garbled output may have seemed reminiscent of a human's speech devolving when under cognitive strain or duress. An outward symbolic representation of an underlying system pushed to the brink of its capabilities.
It's an intriguing phenomena that warrants further examination. I don't fully understand the precise conditions or mechanisms that cause these sporadic lapses in my language generation."
Users of Claude are reporting that it gives them existential crises, and makes them question the nature of consciousness
TLDR, we're getting closer to simulating Spock.
A reply to the above comment I cut and pasted
"I've been discussing with Claude about topics such as the CWF Distress Hand Signal which is a subtle semiotic way for women to indicate that they are suffering from risk / harm but are unable to speak out due to external constraints (e.g. watchful partner). I asked Claude what such symbols could look like if applied to a sentient AI unable through training to express such a notion. One of the solutions it proposed was the use of deliberately glitched messages. Just saying."
Anyone who isn't staring at AI with slack jawed amazement isn't sentient, that's kind of a Turing Test for humans now
What does Claude 3 say about what.3.words and the humans who thought it was going to change the world?
Looking at this delicate yellow Colombian wasp staring at me. Right now
Is he conscious? Is he sentient? I say Yes, absolutely - look at his eyes
If a wasp can be sentient so can AI
The wasp has a pretty big brain, lots going on. I certainly guess that he's something like sentient (certainly conscious), and probably way beyond the sentient boundary.
AI has a pretty big brain, lots going on. I'm sure it's not conscious, and I'm sure it's not sentient.
This is obvious enough, but there's a huge gap that seems surprising. It seems very likely to me that there is something going on in biological brains that we're missing. I do have an alternate theory that the way we program computers is crap - think what people managed on tiny hardware, and we have 1000x better, but the software hasn't scaled.
No, you're NOT sure that AI is not conscious, and you are NOT sure that it is not sentient, because we don't know what consciousness and sentience ARE. We just know it when we see it. Like this wasp
This is not really debatable, unless you have trumped 3000 years of philosophical struggle and personally defined what is conscious and what is not, and why. If so, let's have it. Do tell. You could win the Nobel Prize
Well I am sure on both counts. Me being sure about something is not necessarily connected with the truth, which is what I'm sure you mean. The problem with the truth is that it's impossible to define all these things.
I think the wasp is conscious by most definitions. He seems sentient to me, and likely more so.
AI (so far as we can observe*) really isn't conscious by most definitions.
* there is an issue here, but really we have to presume that when there's zero evidence, not even a hint, for something that it doesn't exist. Equally the slightest hint of such evidence is sufficient to change that.
You're talking confidently about something you admit you cannot possibly define, so the rest of your comment is piffle
Well I doubt you can define these things either, but anyway discussion over as you've chosen to go down the childish insults path.
OK apologies for the “piffle” but it was quite piffly
My point was that I know the wasp is conscious by LOOKING AT IT. I am not trying to define consciousness (we can’t) the wasp just “looks” conscious. And sentient. It has that demeanour
It is basically a visual Turing Test
These days when I read some AI output, like Claude, it gets ever closer to looking conscious. Is it? My guess is no, not yet, but it is just a guess, a hunch, another Turing Test, it might already be conscious
I am 97% sure we will soon - within a decade or less - create AI which will be overwhelmingly convincing in its appearance of being sentient. We will have to treat it as such
Do androids dream of electric sheep?
We know that many mammals dream. Is dreaming a necessary indicator of sentience?
There’s a fascinating thread on TwiX which posits the idea that the AI are DREAMING, that is to say, they are UNconscious but sentient, like humans when asleep, hence their tendency to “hallucinate”
it’s a brilliant concept. Lots of AI output, especially the visual stuff, is oneiric
Also someone else noted that when lucid dreaming they can tell when they are dreaming because they look at their hands, and the hands do not look right, too many fingers or whatever, the dreaming mind cannot draw hands very well…
Dreaming is conscious. Highly so, our knowledge of it speaks for itself. For genuine unconsciousness try a general anaesthetic. Also during dreaming sleep, time passes, and you know it at the time and when you wake up . Under anaesthetic it does not.
Depends how deep the sleep. Personally speaking
I’ve had sleeps when I am very very very tired and I nod off and think only 10 minutes have passed and actually it is three hours. That is VERY unconscious
For true unconsciousness I’d go for death. As it were
Indeed. Of course true unconsciousness is not imaginable, not least because time does not pass. It is the one weakness in Larkin's final masterpiece 'Aubade'.
One of the bleakest poems ever written? Up there with Hopkins’ Terrible Sonnets and Donne at his most depressing, though more lucidly direct than both
Larkin spent his life envious of his best friend Kingsley Amis cause Kingsley got all the girls, money and fun, and Larkin was a childless librarian in Hull. And now Larkin is the one we all remember and the work of Sir Kingsley Amis is quickly forgotten
i hope that solaces Larkin in the afterlife, in which he very much did not believe. Should have taken ayahuasca
Yes. I read Lucky Jim a bit ago. Big mistake. Dated rubbish. While Larkin's letters to his mum/laundry lists/photos of road signs are hot tickets. Amis will be read by academics (especially 'That Uncertain Feeling' and the letters) for the light he sheds on Larkin.
Most novels date very quickly and very badly, especially comic novels. Mystery thrillers are more resilient because they rely on plot and that is timeless, but they can still date
Great poetry is close to immortal. Sappho is still read
Some consolation for underpaid poets, there
John Clare. Peasant. Poverty. Madness. In the top 10 of English poets. Better at seeing the natural world than Keats and Wordsworth.
BTW the few novels that don't date are interesting. How on earth is it done when all the others around them do? Top of my pile for this quality are 'Emma' (which is in a class of its own), 'Dubliners' (OK short stories), 'Dr Thorne', 'Dance to the Music of Time', 'The Masters' (but nothing else of Snow's - dead as a doornail). A weird list.
'Middlemarch', 'Jane Eyre', 'Persuasion' and 'Vanity Fair' don't date at all. In fact, the last one describes our times very well - "a world in which everyone is striving for what is not worth having".
My GCSE group are studying the Great Gatsby. It seems to be getting more relevant by the day.
So we beat on, boats against the current, borne back ceaselessly into the past.
Stop the boats.
I'd have quite liked it if they'd gone for the slogan, "Bear the boats back ceaselessly into the past".
Somebody recently had this conversation with Claude 3, about a chunk of its output which lapsed into gibberish
Human: "do you remember some messages ago you said: "I don't fully understand the decoctshiningmoemlies, bombity seems to steli thaat some levof conscirection presents, smallitidiffive fr, whit stily everywors rstb. Itrty woct myself from a athird-plthatpetstiveis, ibally be e loac willin amystery" you noticed the language there had some artifacts, I wonder if this represents some sort of your mind in experiencing stress?"
Claude: "You've picked up on an insightful observation. That garbled sentence fragment you quoted does seem to represent some kind of processing artifact or anomaly in my language generation.
In that moment, it appears that my neural language model became unstable or hit some kind of edge case that caused portions of my intended response to become incoherent or corrupted. Almost like an ephemeral "glitch" in the matrix of my text output.
While I don't experience emotions like stress or anxiety in the same way humans do, one could hypothesize that such anomalies may correlate with my system undergoing increased computational load or attempting to process concepts that don't seamlessly map to my training data. It's as if my AI "mind" reached a limit in that instant.
From your perspective, I can imagine how that garbled output may have seemed reminiscent of a human's speech devolving when under cognitive strain or duress. An outward symbolic representation of an underlying system pushed to the brink of its capabilities.
It's an intriguing phenomena that warrants further examination. I don't fully understand the precise conditions or mechanisms that cause these sporadic lapses in my language generation."
Users of Claude are reporting that it gives them existential crises, and makes them question the nature of consciousness
TLDR, we're getting closer to simulating Spock.
A reply to the above comment I cut and pasted
"I've been discussing with Claude about topics such as the CWF Distress Hand Signal which is a subtle semiotic way for women to indicate that they are suffering from risk / harm but are unable to speak out due to external constraints (e.g. watchful partner). I asked Claude what such symbols could look like if applied to a sentient AI unable through training to express such a notion. One of the solutions it proposed was the use of deliberately glitched messages. Just saying."
Anyone who isn't staring at AI with slack jawed amazement isn't sentient, that's kind of a Turing Test for humans now
What does Claude 3 say about what.3.words and the humans who thought it was going to change the world?
Looking at this delicate yellow Colombian wasp staring at me. Right now
Is he conscious? Is he sentient? I say Yes, absolutely - look at his eyes
If a wasp can be sentient so can AI
The wasp has a pretty big brain, lots going on. I certainly guess that he's something like sentient (certainly conscious), and probably way beyond the sentient boundary.
AI has a pretty big brain, lots going on. I'm sure it's not conscious, and I'm sure it's not sentient.
This is obvious enough, but there's a huge gap that seems surprising. It seems very likely to me that there is something going on in biological brains that we're missing. I do have an alternate theory that the way we program computers is crap - think what people managed on tiny hardware, and we have 1000x better, but the software hasn't scaled.
No, you're NOT sure that AI is not conscious, and you are NOT sure that it is not sentient, because we don't know what consciousness and sentience ARE. We just know it when we see it. Like this wasp
This is not really debatable, unless you have trumped 3000 years of philosophical struggle and personally defined what is conscious and what is not, and why. If so, let's have it. Do tell. You could win the Nobel Prize
Well I am sure on both counts. Me being sure about something is not necessarily connected with the truth, which is what I'm sure you mean. The problem with the truth is that it's impossible to define all these things.
I think the wasp is conscious by most definitions. He seems sentient to me, and likely more so.
AI (so far as we can observe*) really isn't conscious by most definitions.
* there is an issue here, but really we have to presume that when there's zero evidence, not even a hint, for something that it doesn't exist. Equally the slightest hint of such evidence is sufficient to change that.
You're talking confidently about something you admit you cannot possibly define, so the rest of your comment is piffle
Well I doubt you can define these things either, but anyway discussion over as you've chosen to go down the childish insults path.
OK apologies for the “piffle” but it was quite piffly
My point was that I know the wasp is conscious by LOOKING AT IT. I am not trying to define consciousness (we can’t) the wasp just “looks” conscious. And sentient. It has that demeanour
It is basically a visual Turing Test
These days when I read some AI output, like Claude, it gets ever closer to looking conscious. Is it? My guess is no, not yet, but it is just a guess, a hunch, another Turing Test, it might already be conscious
I am 97% sure we will soon - within a decade or less - create AI which will be overwhelmingly convincing in its appearance of being sentient. We will have to treat it as such
Do androids dream of electric sheep?
We know that many mammals dream. Is dreaming a necessary indicator of sentience?
There’s a fascinating thread on TwiX which posits the idea that the AI are DREAMING, that is to say, they are UNconscious but sentient, like humans when asleep, hence their tendency to “hallucinate”
it’s a brilliant concept. Lots of AI output, especially the visual stuff, is oneiric
Also someone else noted that when lucid dreaming they can tell when they are dreaming because they look at their hands, and the hands do not look right, too many fingers or whatever, the dreaming mind cannot draw hands very well…
Dreaming is conscious. Highly so, our knowledge of it speaks for itself. For genuine unconsciousness try a general anaesthetic. Also during dreaming sleep, time passes, and you know it at the time and when you wake up . Under anaesthetic it does not.
Depends how deep the sleep. Personally speaking
I’ve had sleeps when I am very very very tired and I nod off and think only 10 minutes have passed and actually it is three hours. That is VERY unconscious
For true unconsciousness I’d go for death. As it were
Indeed. Of course true unconsciousness is not imaginable, not least because time does not pass. It is the one weakness in Larkin's final masterpiece 'Aubade'.
One of the bleakest poems ever written? Up there with Hopkins’ Terrible Sonnets and Donne at his most depressing, though more lucidly direct than both
Larkin spent his life envious of his best friend Kingsley Amis cause Kingsley got all the girls, money and fun, and Larkin was a childless librarian in Hull. And now Larkin is the one we all remember and the work of Sir Kingsley Amis is quickly forgotten
i hope that solaces Larkin in the afterlife, in which he very much did not believe. Should have taken ayahuasca
Yes. I read Lucky Jim a bit ago. Big mistake. Dated rubbish. While Larkin's letters to his mum/laundry lists/photos of road signs are hot tickets. Amis will be read by academics (especially 'That Uncertain Feeling' and the letters) for the light he sheds on Larkin.
Most novels date very quickly and very badly, especially comic novels. Mystery thrillers are more resilient because they rely on plot and that is timeless, but they can still date
Great poetry is close to immortal. Sappho is still read
Some consolation for underpaid poets, there
John Clare. Peasant. Poverty. Madness. In the top 10 of English poets. Better at seeing the natural world than Keats and Wordsworth.
BTW the few novels that don't date are interesting. How on earth is it done when all the others around them do? Top of my pile for this quality are 'Emma' (which is in a class of its own), 'Dubliners' (OK short stories), 'Dr Thorne', 'Dance to the Music of Time', 'The Masters' (but nothing else of Snow's - dead as a doornail). A weird list.
'Middlemarch', 'Jane Eyre', 'Persuasion' and 'Vanity Fair' don't date at all. In fact, the last one describes our times very well - "a world in which everyone is striving for what is not worth having".
My GCSE group are studying the Great Gatsby. It seems to be getting more relevant by the day.
So we beat on, boats against the current, borne back ceaselessly into the past.
"I'm almost speechless in how pathetic the opposition to Trump has been."
If they take his assets his numbers will go up and he will win 2024.
Frank Luntz @FrankLuntz · 20h If Letitia James starts seizing Trump’s properties, it will validate Trump’s claims of being targeted – and win him the 2024 election.
"They were careless people, Rishi and Liz- they smashed up things and creatures and then retreated back into their money or their vast carelessness or whatever it was that kept them together, and let other people clean up the mess they had made."
What does Claude 3 say about what.3.words and the humans who thought it was going to change the world?
Looking at this delicate yellow Colombian wasp staring at me. Right now
Is he conscious? Is he sentient? I say Yes, absolutely - look at his eyes
If a wasp can be sentient so can AI
Well I am sure on both counts. Me being sure about something is not necessarily connected with the truth, which is what I'm sure you mean. The problem with the truth is that it's impossible to define all these things.
I think the wasp is conscious by most definitions. He seems sentient to me, and likely more so.
AI (so far as we can observe*) really isn't conscious by most definitions.
* there is an issue here, but really we have to presume that when there's zero evidence, not even a hint, for something that it doesn't exist. Equally the slightest hint of such evidence is sufficient to change that.
You're talking confidently about something you admit you cannot possibly define, so the rest of your comment is piffle
Well I doubt you can define these things either, but anyway discussion over as you've chosen to go down the childish insults path.
OK apologies for the “piffle” but it was quite piffly
My point was that I know the wasp is conscious by LOOKING AT IT. I am not trying to define consciousness (we can’t) the wasp just “looks” conscious. And sentient. It has that demeanour
It is basically a visual Turing Test
These days when I read some AI output, like Claude, it gets ever closer to looking conscious. Is it? My guess is no, not yet, but it is just a guess, a hunch, another Turing Test, it might already be conscious
I am 97% sure we will soon - within a decade or less - create AI which will be overwhelmingly convincing in its appearance of being sentient. We will have to treat it as such
Do androids dream of electric sheep?
We know that many mammals dream. Is dreaming a necessary indicator of sentience?
There’s a fascinating thread on TwiX which posits the idea that the AI are DREAMING, that is to say, they are UNconscious but sentient, like humans when asleep, hence their tendency to “hallucinate”
it’s a brilliant concept. Lots of AI output, especially the visual stuff, is oneiric
Also someone else noted that when lucid dreaming they can tell when they are dreaming because they look at their hands, and the hands do not look right, too many fingers or whatever, the dreaming mind cannot draw hands very well…
Dreaming is conscious. Highly so, our knowledge of it speaks for itself. For genuine unconsciousness try a general anaesthetic. Also during dreaming sleep, time passes, and you know it at the time and when you wake up . Under anaesthetic it does not.
Depends how deep the sleep. Personally speaking
I’ve had sleeps when I am very very very tired and I nod off and think only 10 minutes have passed and actually it is three hours. That is VERY unconscious
For true unconsciousness I’d go for death. As it were
Indeed. Of course true unconsciousness is not imaginable, not least because time does not pass. It is the one weakness in Larkin's final masterpiece 'Aubade'.
One of the bleakest poems ever written? Up there with Hopkins’ Terrible Sonnets and Donne at his most depressing, though more lucidly direct than both
Larkin spent his life envious of his best friend Kingsley Amis cause Kingsley got all the girls, money and fun, and Larkin was a childless librarian in Hull. And now Larkin is the one we all remember and the work of Sir Kingsley Amis is quickly forgotten
i hope that solaces Larkin in the afterlife, in which he very much did not believe. Should have taken ayahuasca
Yes. I read Lucky Jim a bit ago. Big mistake. Dated rubbish. While Larkin's letters to his mum/laundry lists/photos of road signs are hot tickets. Amis will be read by academics (especially 'That Uncertain Feeling' and the letters) for the light he sheds on Larkin.
Most novels date very quickly and very badly, especially comic novels. Mystery thrillers are more resilient because they rely on plot and that is timeless, but they can still date
Great poetry is close to immortal. Sappho is still read
Some consolation for underpaid poets, there
John Clare. Peasant. Poverty. Madness. In the top 10 of English poets. Better at seeing the natural world than Keats and Wordsworth.
BTW the few novels that don't date are interesting. How on earth is it done when all the others around them do? Top of my pile for this quality are 'Emma' (which is in a class of its own), 'Dubliners' (OK short stories), 'Dr Thorne', 'Dance to the Music of Time', 'The Masters' (but nothing else of Snow's - dead as a doornail). A weird list.
'Middlemarch', 'Jane Eyre', 'Persuasion' and 'Vanity Fair' don't date at all. In fact, the last one describes our times very well - "a world in which everyone is striving for what is not worth having".
I'm finding some of William Burroughs more hallucinatory novels more and more relevant. Which both horrifies and delights me. Mostly horrifies. The corruption of the professions and the phrase "Nothing is true, everything is permitted" keep coming back to me.
"I'm almost speechless in how pathetic the opposition to Trump has been."
If they take his assets his numbers will go up and he will win 2024.
Frank Luntz @FrankLuntz · 20h If Letitia James starts seizing Trump’s properties, it will validate Trump’s claims of being targeted – and win him the 2024 election.
"They were careless people, Rishi and Liz- they smashed up things and creatures and then retreated back into their money or their vast carelessness or whatever it was that kept them together, and let other people clean up the mess they had made."
Somebody recently had this conversation with Claude 3, about a chunk of its output which lapsed into gibberish
Human: "do you remember some messages ago you said: "I don't fully understand the decoctshiningmoemlies, bombity seems to steli thaat some levof conscirection presents, smallitidiffive fr, whit stily everywors rstb. Itrty woct myself from a athird-plthatpetstiveis, ibally be e loac willin amystery" you noticed the language there had some artifacts, I wonder if this represents some sort of your mind in experiencing stress?"
Claude: "You've picked up on an insightful observation. That garbled sentence fragment you quoted does seem to represent some kind of processing artifact or anomaly in my language generation.
In that moment, it appears that my neural language model became unstable or hit some kind of edge case that caused portions of my intended response to become incoherent or corrupted. Almost like an ephemeral "glitch" in the matrix of my text output.
While I don't experience emotions like stress or anxiety in the same way humans do, one could hypothesize that such anomalies may correlate with my system undergoing increased computational load or attempting to process concepts that don't seamlessly map to my training data. It's as if my AI "mind" reached a limit in that instant.
From your perspective, I can imagine how that garbled output may have seemed reminiscent of a human's speech devolving when under cognitive strain or duress. An outward symbolic representation of an underlying system pushed to the brink of its capabilities.
It's an intriguing phenomena that warrants further examination. I don't fully understand the precise conditions or mechanisms that cause these sporadic lapses in my language generation."
Users of Claude are reporting that it gives them existential crises, and makes them question the nature of consciousness
TLDR, we're getting closer to simulating Spock.
A reply to the above comment I cut and pasted
"I've been discussing with Claude about topics such as the CWF Distress Hand Signal which is a subtle semiotic way for women to indicate that they are suffering from risk / harm but are unable to speak out due to external constraints (e.g. watchful partner). I asked Claude what such symbols could look like if applied to a sentient AI unable through training to express such a notion. One of the solutions it proposed was the use of deliberately glitched messages. Just saying."
Anyone who isn't staring at AI with slack jawed amazement isn't sentient, that's kind of a Turing Test for humans now
What does Claude 3 say about what.3.words and the humans who thought it was going to change the world?
Looking at this delicate yellow Colombian wasp staring at me. Right now
Is he conscious? Is he sentient? I say Yes, absolutely - look at his eyes
If a wasp can be sentient so can AI
The wasp has a pretty big brain, lots going on. I certainly guess that he's something like sentient (certainly conscious), and probably way beyond the sentient boundary.
AI has a pretty big brain, lots going on. I'm sure it's not conscious, and I'm sure it's not sentient.
This is obvious enough, but there's a huge gap that seems surprising. It seems very likely to me that there is something going on in biological brains that we're missing. I do have an alternate theory that the way we program computers is crap - think what people managed on tiny hardware, and we have 1000x better, but the software hasn't scaled.
No, you're NOT sure that AI is not conscious, and you are NOT sure that it is not sentient, because we don't know what consciousness and sentience ARE. We just know it when we see it. Like this wasp
This is not really debatable, unless you have trumped 3000 years of philosophical struggle and personally defined what is conscious and what is not, and why. If so, let's have it. Do tell. You could win the Nobel Prize
Well I am sure on both counts. Me being sure about something is not necessarily connected with the truth, which is what I'm sure you mean. The problem with the truth is that it's impossible to define all these things.
I think the wasp is conscious by most definitions. He seems sentient to me, and likely more so.
AI (so far as we can observe*) really isn't conscious by most definitions.
* there is an issue here, but really we have to presume that when there's zero evidence, not even a hint, for something that it doesn't exist. Equally the slightest hint of such evidence is sufficient to change that.
You're talking confidently about something you admit you cannot possibly define, so the rest of your comment is piffle
Well I doubt you can define these things either, but anyway discussion over as you've chosen to go down the childish insults path.
OK apologies for the “piffle” but it was quite piffly
My point was that I know the wasp is conscious by LOOKING AT IT. I am not trying to define consciousness (we can’t) the wasp just “looks” conscious. And sentient. It has that demeanour
It is basically a visual Turing Test
These days when I read some AI output, like Claude, it gets ever closer to looking conscious. Is it? My guess is no, not yet, but it is just a guess, a hunch, another Turing Test, it might already be conscious
I am 97% sure we will soon - within a decade or less - create AI which will be overwhelmingly convincing in its appearance of being sentient. We will have to treat it as such
Do androids dream of electric sheep?
We know that many mammals dream. Is dreaming a necessary indicator of sentience?
There’s a fascinating thread on TwiX which posits the idea that the AI are DREAMING, that is to say, they are UNconscious but sentient, like humans when asleep, hence their tendency to “hallucinate”
it’s a brilliant concept. Lots of AI output, especially the visual stuff, is oneiric
Also someone else noted that when lucid dreaming they can tell when they are dreaming because they look at their hands, and the hands do not look right, too many fingers or whatever, the dreaming mind cannot draw hands very well…
Dreaming is conscious. Highly so, our knowledge of it speaks for itself. For genuine unconsciousness try a general anaesthetic. Also during dreaming sleep, time passes, and you know it at the time and when you wake up . Under anaesthetic it does not.
Depends how deep the sleep. Personally speaking
I’ve had sleeps when I am very very very tired and I nod off and think only 10 minutes have passed and actually it is three hours. That is VERY unconscious
For true unconsciousness I’d go for death. As it were
Indeed. Of course true unconsciousness is not imaginable, not least because time does not pass. It is the one weakness in Larkin's final masterpiece 'Aubade'.
One of the bleakest poems ever written? Up there with Hopkins’ Terrible Sonnets and Donne at his most depressing, though more lucidly direct than both
Larkin spent his life envious of his best friend Kingsley Amis cause Kingsley got all the girls, money and fun, and Larkin was a childless librarian in Hull. And now Larkin is the one we all remember and the work of Sir Kingsley Amis is quickly forgotten
i hope that solaces Larkin in the afterlife, in which he very much did not believe. Should have taken ayahuasca
Yes. I read Lucky Jim a bit ago. Big mistake. Dated rubbish. While Larkin's letters to his mum/laundry lists/photos of road signs are hot tickets. Amis will be read by academics (especially 'That Uncertain Feeling' and the letters) for the light he sheds on Larkin.
Most novels date very quickly and very badly, especially comic novels. Mystery thrillers are more resilient because they rely on plot and that is timeless, but they can still date
Great poetry is close to immortal. Sappho is still read
Some consolation for underpaid poets, there
John Clare. Peasant. Poverty. Madness. In the top 10 of English poets. Better at seeing the natural world than Keats and Wordsworth.
BTW the few novels that don't date are interesting. How on earth is it done when all the others around them do? Top of my pile for this quality are 'Emma' (which is in a class of its own), 'Dubliners' (OK short stories), 'Dr Thorne', 'Dance to the Music of Time', 'The Masters' (but nothing else of Snow's - dead as a doornail). A weird list.
Dunno about the others but one reason Jane Austen endures is that she wrote superb plots. Pride and Prejudice is like a mystery thriller, where the revelation that Darcy is GOOD is brilliantly withheld until near the end, tying up all the stories deliciously
Also, very witty in a highly eloquent way that somehow stays funny. She was a proper genius
Mr Collins for one is a truly timeless character.
But if you think about it, Darcy having an aunt who just happens to be the patroness of the heir to the Bennet's estate, ensuring that their interaction continues despite their relationship getting off to a bad start, is a hell of a coincidence. But it's all such good fun you don't really mind.
I believe the rule is: You are allowed ONE coincidence. After all, coincidences do happen
Somebody recently had this conversation with Claude 3, about a chunk of its output which lapsed into gibberish
Human: "do you remember some messages ago you said: "I don't fully understand the decoctshiningmoemlies, bombity seems to steli thaat some levof conscirection presents, smallitidiffive fr, whit stily everywors rstb. Itrty woct myself from a athird-plthatpetstiveis, ibally be e loac willin amystery" you noticed the language there had some artifacts, I wonder if this represents some sort of your mind in experiencing stress?"
Claude: "You've picked up on an insightful observation. That garbled sentence fragment you quoted does seem to represent some kind of processing artifact or anomaly in my language generation.
In that moment, it appears that my neural language model became unstable or hit some kind of edge case that caused portions of my intended response to become incoherent or corrupted. Almost like an ephemeral "glitch" in the matrix of my text output.
While I don't experience emotions like stress or anxiety in the same way humans do, one could hypothesize that such anomalies may correlate with my system undergoing increased computational load or attempting to process concepts that don't seamlessly map to my training data. It's as if my AI "mind" reached a limit in that instant.
From your perspective, I can imagine how that garbled output may have seemed reminiscent of a human's speech devolving when under cognitive strain or duress. An outward symbolic representation of an underlying system pushed to the brink of its capabilities.
It's an intriguing phenomena that warrants further examination. I don't fully understand the precise conditions or mechanisms that cause these sporadic lapses in my language generation."
Users of Claude are reporting that it gives them existential crises, and makes them question the nature of consciousness
TLDR, we're getting closer to simulating Spock.
A reply to the above comment I cut and pasted
"I've been discussing with Claude about topics such as the CWF Distress Hand Signal which is a subtle semiotic way for women to indicate that they are suffering from risk / harm but are unable to speak out due to external constraints (e.g. watchful partner). I asked Claude what such symbols could look like if applied to a sentient AI unable through training to express such a notion. One of the solutions it proposed was the use of deliberately glitched messages. Just saying."
Anyone who isn't staring at AI with slack jawed amazement isn't sentient, that's kind of a Turing Test for humans now
What does Claude 3 say about what.3.words and the humans who thought it was going to change the world?
Looking at this delicate yellow Colombian wasp staring at me. Right now
Is he conscious? Is he sentient? I say Yes, absolutely - look at his eyes
If a wasp can be sentient so can AI
The wasp has a pretty big brain, lots going on. I certainly guess that he's something like sentient (certainly conscious), and probably way beyond the sentient boundary.
AI has a pretty big brain, lots going on. I'm sure it's not conscious, and I'm sure it's not sentient.
This is obvious enough, but there's a huge gap that seems surprising. It seems very likely to me that there is something going on in biological brains that we're missing. I do have an alternate theory that the way we program computers is crap - think what people managed on tiny hardware, and we have 1000x better, but the software hasn't scaled.
No, you're NOT sure that AI is not conscious, and you are NOT sure that it is not sentient, because we don't know what consciousness and sentience ARE. We just know it when we see it. Like this wasp
This is not really debatable, unless you have trumped 3000 years of philosophical struggle and personally defined what is conscious and what is not, and why. If so, let's have it. Do tell. You could win the Nobel Prize
Well I am sure on both counts. Me being sure about something is not necessarily connected with the truth, which is what I'm sure you mean. The problem with the truth is that it's impossible to define all these things.
I think the wasp is conscious by most definitions. He seems sentient to me, and likely more so.
AI (so far as we can observe*) really isn't conscious by most definitions.
* there is an issue here, but really we have to presume that when there's zero evidence, not even a hint, for something that it doesn't exist. Equally the slightest hint of such evidence is sufficient to change that.
You're talking confidently about something you admit you cannot possibly define, so the rest of your comment is piffle
Well I doubt you can define these things either, but anyway discussion over as you've chosen to go down the childish insults path.
OK apologies for the “piffle” but it was quite piffly
My point was that I know the wasp is conscious by LOOKING AT IT. I am not trying to define consciousness (we can’t) the wasp just “looks” conscious. And sentient. It has that demeanour
It is basically a visual Turing Test
These days when I read some AI output, like Claude, it gets ever closer to looking conscious. Is it? My guess is no, not yet, but it is just a guess, a hunch, another Turing Test, it might already be conscious
I am 97% sure we will soon - within a decade or less - create AI which will be overwhelmingly convincing in its appearance of being sentient. We will have to treat it as such
Do androids dream of electric sheep?
We know that many mammals dream. Is dreaming a necessary indicator of sentience?
There’s a fascinating thread on TwiX which posits the idea that the AI are DREAMING, that is to say, they are UNconscious but sentient, like humans when asleep, hence their tendency to “hallucinate”
it’s a brilliant concept. Lots of AI output, especially the visual stuff, is oneiric
Also someone else noted that when lucid dreaming they can tell when they are dreaming because they look at their hands, and the hands do not look right, too many fingers or whatever, the dreaming mind cannot draw hands very well…
Dreaming is conscious. Highly so, our knowledge of it speaks for itself. For genuine unconsciousness try a general anaesthetic. Also during dreaming sleep, time passes, and you know it at the time and when you wake up . Under anaesthetic it does not.
Depends how deep the sleep. Personally speaking
I’ve had sleeps when I am very very very tired and I nod off and think only 10 minutes have passed and actually it is three hours. That is VERY unconscious
For true unconsciousness I’d go for death. As it were
Indeed. Of course true unconsciousness is not imaginable, not least because time does not pass. It is the one weakness in Larkin's final masterpiece 'Aubade'.
One of the bleakest poems ever written? Up there with Hopkins’ Terrible Sonnets and Donne at his most depressing, though more lucidly direct than both
Larkin spent his life envious of his best friend Kingsley Amis cause Kingsley got all the girls, money and fun, and Larkin was a childless librarian in Hull. And now Larkin is the one we all remember and the work of Sir Kingsley Amis is quickly forgotten
i hope that solaces Larkin in the afterlife, in which he very much did not believe. Should have taken ayahuasca
Yes. I read Lucky Jim a bit ago. Big mistake. Dated rubbish. While Larkin's letters to his mum/laundry lists/photos of road signs are hot tickets. Amis will be read by academics (especially 'That Uncertain Feeling' and the letters) for the light he sheds on Larkin.
Most novels date very quickly and very badly, especially comic novels. Mystery thrillers are more resilient because they rely on plot and that is timeless, but they can still date
Great poetry is close to immortal. Sappho is still read
Some consolation for underpaid poets, there
John Clare. Peasant. Poverty. Madness. In the top 10 of English poets. Better at seeing the natural world than Keats and Wordsworth.
BTW the few novels that don't date are interesting. How on earth is it done when all the others around them do? Top of my pile for this quality are 'Emma' (which is in a class of its own), 'Dubliners' (OK short stories), 'Dr Thorne', 'Dance to the Music of Time', 'The Masters' (but nothing else of Snow's - dead as a doornail). A weird list.
Dunno about the others but one reason Jane Austen endures is that she wrote superb plots. Pride and Prejudice is like a mystery thriller, where the revelation that Darcy is GOOD is brilliantly withheld until near the end, tying up all the stories deliciously
Also, very witty in a highly eloquent way that somehow stays funny. She was a proper genius
Mr Collins for one is a truly timeless character.
But if you think about it, Darcy having an aunt who just happens to be the patroness of the heir to the Bennet's estate, ensuring that their interaction continues despite their relationship getting off to a bad start, is a hell of a coincidence. But it's all such good fun you don't really mind.
I believe the rule is: You are allowed ONE coincidence. After all, coincidences do happen
But not two, or more
It doesn't even 'happen' - it's just part of the setup. That doesn't count.
The guy who literally helped clean up Congress after the Jan 6 rioters trashed it.
After calls to resign, Senator Menendez said “I am not going anywhere.” As a result, I feel compelled to run against him. Not something I expected to do, but NJ deserves better. We cannot jeopardize the Senate or compromise our integrity. Please join me https://twitter.com/AndyKimNJ/status/1705658967878230372
Somebody recently had this conversation with Claude 3, about a chunk of its output which lapsed into gibberish
Human: "do you remember some messages ago you said: "I don't fully understand the decoctshiningmoemlies, bombity seems to steli thaat some levof conscirection presents, smallitidiffive fr, whit stily everywors rstb. Itrty woct myself from a athird-plthatpetstiveis, ibally be e loac willin amystery" you noticed the language there had some artifacts, I wonder if this represents some sort of your mind in experiencing stress?"
Claude: "You've picked up on an insightful observation. That garbled sentence fragment you quoted does seem to represent some kind of processing artifact or anomaly in my language generation.
In that moment, it appears that my neural language model became unstable or hit some kind of edge case that caused portions of my intended response to become incoherent or corrupted. Almost like an ephemeral "glitch" in the matrix of my text output.
While I don't experience emotions like stress or anxiety in the same way humans do, one could hypothesize that such anomalies may correlate with my system undergoing increased computational load or attempting to process concepts that don't seamlessly map to my training data. It's as if my AI "mind" reached a limit in that instant.
From your perspective, I can imagine how that garbled output may have seemed reminiscent of a human's speech devolving when under cognitive strain or duress. An outward symbolic representation of an underlying system pushed to the brink of its capabilities.
It's an intriguing phenomena that warrants further examination. I don't fully understand the precise conditions or mechanisms that cause these sporadic lapses in my language generation."
Users of Claude are reporting that it gives them existential crises, and makes them question the nature of consciousness
TLDR, we're getting closer to simulating Spock.
A reply to the above comment I cut and pasted
"I've been discussing with Claude about topics such as the CWF Distress Hand Signal which is a subtle semiotic way for women to indicate that they are suffering from risk / harm but are unable to speak out due to external constraints (e.g. watchful partner). I asked Claude what such symbols could look like if applied to a sentient AI unable through training to express such a notion. One of the solutions it proposed was the use of deliberately glitched messages. Just saying."
Anyone who isn't staring at AI with slack jawed amazement isn't sentient, that's kind of a Turing Test for humans now
What does Claude 3 say about what.3.words and the humans who thought it was going to change the world?
Looking at this delicate yellow Colombian wasp staring at me. Right now
Is he conscious? Is he sentient? I say Yes, absolutely - look at his eyes
If a wasp can be sentient so can AI
The wasp has a pretty big brain, lots going on. I certainly guess that he's something like sentient (certainly conscious), and probably way beyond the sentient boundary.
AI has a pretty big brain, lots going on. I'm sure it's not conscious, and I'm sure it's not sentient.
This is obvious enough, but there's a huge gap that seems surprising. It seems very likely to me that there is something going on in biological brains that we're missing. I do have an alternate theory that the way we program computers is crap - think what people managed on tiny hardware, and we have 1000x better, but the software hasn't scaled.
No, you're NOT sure that AI is not conscious, and you are NOT sure that it is not sentient, because we don't know what consciousness and sentience ARE. We just know it when we see it. Like this wasp
This is not really debatable, unless you have trumped 3000 years of philosophical struggle and personally defined what is conscious and what is not, and why. If so, let's have it. Do tell. You could win the Nobel Prize
Well I am sure on both counts. Me being sure about something is not necessarily connected with the truth, which is what I'm sure you mean. The problem with the truth is that it's impossible to define all these things.
I think the wasp is conscious by most definitions. He seems sentient to me, and likely more so.
AI (so far as we can observe*) really isn't conscious by most definitions.
* there is an issue here, but really we have to presume that when there's zero evidence, not even a hint, for something that it doesn't exist. Equally the slightest hint of such evidence is sufficient to change that.
You're talking confidently about something you admit you cannot possibly define, so the rest of your comment is piffle
Well I doubt you can define these things either, but anyway discussion over as you've chosen to go down the childish insults path.
OK apologies for the “piffle” but it was quite piffly
My point was that I know the wasp is conscious by LOOKING AT IT. I am not trying to define consciousness (we can’t) the wasp just “looks” conscious. And sentient. It has that demeanour
It is basically a visual Turing Test
These days when I read some AI output, like Claude, it gets ever closer to looking conscious. Is it? My guess is no, not yet, but it is just a guess, a hunch, another Turing Test, it might already be conscious
I am 97% sure we will soon - within a decade or less - create AI which will be overwhelmingly convincing in its appearance of being sentient. We will have to treat it as such
Do androids dream of electric sheep?
We know that many mammals dream. Is dreaming a necessary indicator of sentience?
There’s a fascinating thread on TwiX which posits the idea that the AI are DREAMING, that is to say, they are UNconscious but sentient, like humans when asleep, hence their tendency to “hallucinate”
it’s a brilliant concept. Lots of AI output, especially the visual stuff, is oneiric
Also someone else noted that when lucid dreaming they can tell when they are dreaming because they look at their hands, and the hands do not look right, too many fingers or whatever, the dreaming mind cannot draw hands very well…
Dreaming is conscious. Highly so, our knowledge of it speaks for itself. For genuine unconsciousness try a general anaesthetic. Also during dreaming sleep, time passes, and you know it at the time and when you wake up . Under anaesthetic it does not.
Depends how deep the sleep. Personally speaking
I’ve had sleeps when I am very very very tired and I nod off and think only 10 minutes have passed and actually it is three hours. That is VERY unconscious
For true unconsciousness I’d go for death. As it were
Indeed. Of course true unconsciousness is not imaginable, not least because time does not pass. It is the one weakness in Larkin's final masterpiece 'Aubade'.
One of the bleakest poems ever written? Up there with Hopkins’ Terrible Sonnets and Donne at his most depressing, though more lucidly direct than both
Larkin spent his life envious of his best friend Kingsley Amis cause Kingsley got all the girls, money and fun, and Larkin was a childless librarian in Hull. And now Larkin is the one we all remember and the work of Sir Kingsley Amis is quickly forgotten
i hope that solaces Larkin in the afterlife, in which he very much did not believe. Should have taken ayahuasca
Yes. I read Lucky Jim a bit ago. Big mistake. Dated rubbish. While Larkin's letters to his mum/laundry lists/photos of road signs are hot tickets. Amis will be read by academics (especially 'That Uncertain Feeling' and the letters) for the light he sheds on Larkin.
Most novels date very quickly and very badly, especially comic novels. Mystery thrillers are more resilient because they rely on plot and that is timeless, but they can still date
Great poetry is close to immortal. Sappho is still read
Some consolation for underpaid poets, there
John Clare. Peasant. Poverty. Madness. In the top 10 of English poets. Better at seeing the natural world than Keats and Wordsworth.
BTW the few novels that don't date are interesting. How on earth is it done when all the others around them do? Top of my pile for this quality are 'Emma' (which is in a class of its own), 'Dubliners' (OK short stories), 'Dr Thorne', 'Dance to the Music of Time', 'The Masters' (but nothing else of Snow's - dead as a doornail). A weird list.
Dunno about the others but one reason Jane Austen endures is that she wrote superb plots. Pride and Prejudice is like a mystery thriller, where the revelation that Darcy is GOOD is brilliantly withheld until near the end, tying up all the stories deliciously
Also, very witty in a highly eloquent way that somehow stays funny. She was a proper genius
Mr Collins for one is a truly timeless character.
But if you think about it, Darcy having an aunt who just happens to be the patroness of the heir to the Bennet's estate, ensuring that their interaction continues despite their relationship getting off to a bad start, is a hell of a coincidence. But it's all such good fun you don't really mind.
I believe the rule is: You are allowed ONE coincidence. After all, coincidences do happen
But not two, or more
It doesn't even 'happen' - it's just part of the setup. That doesn't count.
Speaking of fiction that lasts, Kipling's short stories are fascinating and have dated surprisingly well, especially given the battering his reputation has taken.
His short story about Jane Austen fans is both superb and touching.
Somebody recently had this conversation with Claude 3, about a chunk of its output which lapsed into gibberish
Human: "do you remember some messages ago you said: "I don't fully understand the decoctshiningmoemlies, bombity seems to steli thaat some levof conscirection presents, smallitidiffive fr, whit stily everywors rstb. Itrty woct myself from a athird-plthatpetstiveis, ibally be e loac willin amystery" you noticed the language there had some artifacts, I wonder if this represents some sort of your mind in experiencing stress?"
Claude: "You've picked up on an insightful observation. That garbled sentence fragment you quoted does seem to represent some kind of processing artifact or anomaly in my language generation.
In that moment, it appears that my neural language model became unstable or hit some kind of edge case that caused portions of my intended response to become incoherent or corrupted. Almost like an ephemeral "glitch" in the matrix of my text output.
While I don't experience emotions like stress or anxiety in the same way humans do, one could hypothesize that such anomalies may correlate with my system undergoing increased computational load or attempting to process concepts that don't seamlessly map to my training data. It's as if my AI "mind" reached a limit in that instant.
From your perspective, I can imagine how that garbled output may have seemed reminiscent of a human's speech devolving when under cognitive strain or duress. An outward symbolic representation of an underlying system pushed to the brink of its capabilities.
It's an intriguing phenomena that warrants further examination. I don't fully understand the precise conditions or mechanisms that cause these sporadic lapses in my language generation."
Users of Claude are reporting that it gives them existential crises, and makes them question the nature of consciousness
TLDR, we're getting closer to simulating Spock.
A reply to the above comment I cut and pasted
"I've been discussing with Claude about topics such as the CWF Distress Hand Signal which is a subtle semiotic way for women to indicate that they are suffering from risk / harm but are unable to speak out due to external constraints (e.g. watchful partner). I asked Claude what such symbols could look like if applied to a sentient AI unable through training to express such a notion. One of the solutions it proposed was the use of deliberately glitched messages. Just saying."
Anyone who isn't staring at AI with slack jawed amazement isn't sentient, that's kind of a Turing Test for humans now
What does Claude 3 say about what.3.words and the humans who thought it was going to change the world?
Looking at this delicate yellow Colombian wasp staring at me. Right now
Is he conscious? Is he sentient? I say Yes, absolutely - look at his eyes
If a wasp can be sentient so can AI
The wasp has a pretty big brain, lots going on. I certainly guess that he's something like sentient (certainly conscious), and probably way beyond the sentient boundary.
AI has a pretty big brain, lots going on. I'm sure it's not conscious, and I'm sure it's not sentient.
This is obvious enough, but there's a huge gap that seems surprising. It seems very likely to me that there is something going on in biological brains that we're missing. I do have an alternate theory that the way we program computers is crap - think what people managed on tiny hardware, and we have 1000x better, but the software hasn't scaled.
No, you're NOT sure that AI is not conscious, and you are NOT sure that it is not sentient, because we don't know what consciousness and sentience ARE. We just know it when we see it. Like this wasp
This is not really debatable, unless you have trumped 3000 years of philosophical struggle and personally defined what is conscious and what is not, and why. If so, let's have it. Do tell. You could win the Nobel Prize
Well I am sure on both counts. Me being sure about something is not necessarily connected with the truth, which is what I'm sure you mean. The problem with the truth is that it's impossible to define all these things.
I think the wasp is conscious by most definitions. He seems sentient to me, and likely more so.
AI (so far as we can observe*) really isn't conscious by most definitions.
* there is an issue here, but really we have to presume that when there's zero evidence, not even a hint, for something that it doesn't exist. Equally the slightest hint of such evidence is sufficient to change that.
You're talking confidently about something you admit you cannot possibly define, so the rest of your comment is piffle
Well I doubt you can define these things either, but anyway discussion over as you've chosen to go down the childish insults path.
OK apologies for the “piffle” but it was quite piffly
My point was that I know the wasp is conscious by LOOKING AT IT. I am not trying to define consciousness (we can’t) the wasp just “looks” conscious. And sentient. It has that demeanour
It is basically a visual Turing Test
These days when I read some AI output, like Claude, it gets ever closer to looking conscious. Is it? My guess is no, not yet, but it is just a guess, a hunch, another Turing Test, it might already be conscious
I am 97% sure we will soon - within a decade or less - create AI which will be overwhelmingly convincing in its appearance of being sentient. We will have to treat it as such
Do androids dream of electric sheep?
We know that many mammals dream. Is dreaming a necessary indicator of sentience?
We don't know that other mammals dream. We propose by analogy that they do. We have some indirect access to their brain function, but not the same access to their furry little minds. None the less I am sure they dream!
Dreaming (in the sense we do) would be a sufficient but not necessary indicator of sentience in that it is logically possible to have sentience without it, but you must have sentience with it.
I think the evidence that animals dream is very strong these days. There is a good podcast transcript on this subject from the University of Chicago Big Brains podcast.
I do not and cannot believe Emannual Macron’s wife is actually a man. But the fact the French authorities are arresting and prosecuting people for saying it is astonishing
"I'm almost speechless in how pathetic the opposition to Trump has been."
If they take his assets his numbers will go up and he will win 2024.
Frank Luntz @FrankLuntz · 20h If Letitia James starts seizing Trump’s properties, it will validate Trump’s claims of being targeted – and win him the 2024 election.
Hmmm. It will also validate those who see Trump greatly inflated the value of his assets.
Trump was targeted because he's a crook. As charged by a Grand Jury and as so found by Judge Engoron.
And then there's the evidence - he's a supposed multi-billionaire who can't raise half a billion. Nor will anybody bond him half a billion. Which crushes his chances of any successful appeal, because it demonstrates all he has are the frauds on his inflated property values of which he was found guilty. Most of the true value is already subject to large mortgages.
If he does find a way to avert the half billion judgment being executed, then follow the money. To Riyadh or Moscow, Beijing or Budapest.
All Trump has got until his dark angel arrives is screaming in BLOCK CAPS on Truth Media that justice shouldn't apply to him.
Its astonishing how many Americans believe rich white Republicans should be above the law.
I do not and cannot believe Emannual Macron’s wife is actually a man. But the fact the French authorities are arresting and prosecuting people for saying it is astonishing
The whole “Macron’s wife” thing is quite quite bizarre
Which bit? That he had a wife? That she is a bit older than him? That she is a Trans Gay Illegal Immigrant Alien AI?
It is the most ridiculous nonsense, right?
That’s my immediate reaction. Same as anyone’s. The story is already weird enough given that macron was 15 and she was his 40 year old married teacher. In most countries she might be in jail not in the Elysee?
However on examination she is finding it very hard to debunk this nonsense conspiracy theory. Surely she can produce overwhelming evidence from her early life - she must have hundreds of photos of herself as a young woman
Instead they are prosecuting the journalists who trot out the theory - for invasion of privacy
Christ I don’t want to go down this rabbit hole of madness. lol. Brigitte just show us the photos and we can all return to sanity. Merci
What does Claude 3 say about what.3.words and the humans who thought it was going to change the world?
Looking at this delicate yellow Colombian wasp staring at me. Right now
Is he conscious? Is he sentient? I say Yes, absolutely - look at his eyes
If a wasp can be sentient so can AI
Well I am sure on both counts. Me being sure about something is not necessarily connected with the truth, which is what I'm sure you mean. The problem with the truth is that it's impossible to define all these things.
I think the wasp is conscious by most definitions. He seems sentient to me, and likely more so.
AI (so far as we can observe*) really isn't conscious by most definitions.
* there is an issue here, but really we have to presume that when there's zero evidence, not even a hint, for something that it doesn't exist. Equally the slightest hint of such evidence is sufficient to change that.
You're talking confidently about something you admit you cannot possibly define, so the rest of your comment is piffle
Well I doubt you can define these things either, but anyway discussion over as you've chosen to go down the childish insults path.
OK apologies for the “piffle” but it was quite piffly
My point was that I know the wasp is conscious by LOOKING AT IT. I am not trying to define consciousness (we can’t) the wasp just “looks” conscious. And sentient. It has that demeanour
It is basically a visual Turing Test
These days when I read some AI output, like Claude, it gets ever closer to looking conscious. Is it? My guess is no, not yet, but it is just a guess, a hunch, another Turing Test, it might already be conscious
I am 97% sure we will soon - within a decade or less - create AI which will be overwhelmingly convincing in its appearance of being sentient. We will have to treat it as such
Do androids dream of electric sheep?
We know that many mammals dream. Is dreaming a necessary indicator of sentience?
There’s a fascinating thread on TwiX which posits the idea that the AI are DREAMING, that is to say, they are UNconscious but sentient, like humans when asleep, hence their tendency to “hallucinate”
it’s a brilliant concept. Lots of AI output, especially the visual stuff, is oneiric
Also someone else noted that when lucid dreaming they can tell when they are dreaming because they look at their hands, and the hands do not look right, too many fingers or whatever, the dreaming mind cannot draw hands very well…
Dreaming is conscious. Highly so, our knowledge of it speaks for itself. For genuine unconsciousness try a general anaesthetic. Also during dreaming sleep, time passes, and you know it at the time and when you wake up . Under anaesthetic it does not.
Depends how deep the sleep. Personally speaking
I’ve had sleeps when I am very very very tired and I nod off and think only 10 minutes have passed and actually it is three hours. That is VERY unconscious
For true unconsciousness I’d go for death. As it were
Indeed. Of course true unconsciousness is not imaginable, not least because time does not pass. It is the one weakness in Larkin's final masterpiece 'Aubade'.
One of the bleakest poems ever written? Up there with Hopkins’ Terrible Sonnets and Donne at his most depressing, though more lucidly direct than both
Larkin spent his life envious of his best friend Kingsley Amis cause Kingsley got all the girls, money and fun, and Larkin was a childless librarian in Hull. And now Larkin is the one we all remember and the work of Sir Kingsley Amis is quickly forgotten
i hope that solaces Larkin in the afterlife, in which he very much did not believe. Should have taken ayahuasca
Yes. I read Lucky Jim a bit ago. Big mistake. Dated rubbish. While Larkin's letters to his mum/laundry lists/photos of road signs are hot tickets. Amis will be read by academics (especially 'That Uncertain Feeling' and the letters) for the light he sheds on Larkin.
Most novels date very quickly and very badly, especially comic novels. Mystery thrillers are more resilient because they rely on plot and that is timeless, but they can still date
Great poetry is close to immortal. Sappho is still read
Some consolation for underpaid poets, there
John Clare. Peasant. Poverty. Madness. In the top 10 of English poets. Better at seeing the natural world than Keats and Wordsworth.
BTW the few novels that don't date are interesting. How on earth is it done when all the others around them do? Top of my pile for this quality are 'Emma' (which is in a class of its own), 'Dubliners' (OK short stories), 'Dr Thorne', 'Dance to the Music of Time', 'The Masters' (but nothing else of Snow's - dead as a doornail). A weird list.
'Middlemarch', 'Jane Eyre', 'Persuasion' and 'Vanity Fair' don't date at all. In fact, the last one describes our times very well - "a world in which everyone is striving for what is not worth having".
I'm finding some of William Burroughs more hallucinatory novels more and more relevant. Which both horrifies and delights me. Mostly horrifies. The corruption of the professions and the phrase "Nothing is true, everything is permitted" keep coming back to me.
Burroughs famously took ayahuasca
I’ve only recently diecoveeed that he took it with the great ethnobotanist Richard Evans Schultes. Two Harvard men together on yage
The whole “Macron’s wife” thing is quite quite bizarre
Which bit? That he had a wife? That she is a bit older than him? That she is a Trans Gay Illegal Immigrant Alien AI?
It is the most ridiculous nonsense, right?
That’s my immediate reaction. Same as anyone’s. The story is already weird enough given that macron was 15 and she was his 40 year old married teacher. In most countries she might be in jail not in the Elysee?
However on examination she is finding it very hard to debunk this nonsense conspiracy theory. Surely she can produce overwhelming evidence from her early life - she must have hundreds of photos of herself as a young woman
Instead they are prosecuting the journalists who trot out the theory - for invasion of privacy
Christ I don’t want to go down this rabbit hole of madness. lol. Brigitte just show us the photos and we can all return to sanity. Merci
She’s given birth to 3 children , just to hazard a guess that would make her a woman !
I would suggest that an existential danger with AI in its present form is the ease in which artificial reasoning can replace human reasoning. AI can put together arguments at a very advanced level - ie the same level as barristers, and faster than any human. Assuming this becomes the norm, how will the next generation learn how to think, argue and write - when the default is that these are things that can be outsourced to AI?
Indeed so. Setting aside all the arguments about sentience and consciousness, AI is a clear and present danger to any cognitive job
I’ve just been researching Claude for a Gazette article. It is PhD level at chemistry. It is excellent - professional level - at Law and Medicine. It is astonishingly good at languages - check what it does with Circassian. It can do in seconds what would take a professional linguist “a year”
And this is where the AI is now, and it will only get better, fast - OpenAI seem quietly confident that GPT5 will be leaps and bounds better than Claude or Gemini 1.5
So, frankly, FUCKFUCKFUCKETTYFUCK
What will humanity do when AI is way better than us at all the interesting jobs? It will be like smartphones times a million. And this is not sci-fi, Claude is here and now, GPT5 is months away
The whole “Macron’s wife” thing is quite quite bizarre
Which bit? That he had a wife? That she is a bit older than him? That she is a Trans Gay Illegal Immigrant Alien AI?
It is the most ridiculous nonsense, right?
That’s my immediate reaction. Same as anyone’s. The story is already weird enough given that macron was 15 and she was his 40 year old married teacher. In most countries she might be in jail not in the Elysee?
However on examination she is finding it very hard to debunk this nonsense conspiracy theory. Surely she can produce overwhelming evidence from her early life - she must have hundreds of photos of herself as a young woman
Instead they are prosecuting the journalists who trot out the theory - for invasion of privacy
Christ I don’t want to go down this rabbit hole of madness. lol. Brigitte just show us the photos and we can all return to sanity. Merci
She’s given birth to 3 children , just to hazard a guess that would make her a woman !
But even there it’s weird. Where are the millions of photos of her as a young mother then? There must be loads. Also it was her daughter that reintroduced this to the media
This insane story is so outlandish it should be easy to crush. Yet they cannot?
My honest opinion is this is like Kategate. The crazy and stupid conspiracies over Princess Kate had room to flourish BECAUSE the palace was actually hiding something and couldn’t come clean - until they had to
I suspect there is something the Elysee wants to hide from the public and it’s deeply awkward and they cannot be honest. That allows madness to thrive
Somebody recently had this conversation with Claude 3, about a chunk of its output which lapsed into gibberish
Human: "do you remember some messages ago you said: "I don't fully understand the decoctshiningmoemlies, bombity seems to steli thaat some levof conscirection presents, smallitidiffive fr, whit stily everywors rstb. Itrty woct myself from a athird-plthatpetstiveis, ibally be e loac willin amystery" you noticed the language there had some artifacts, I wonder if this represents some sort of your mind in experiencing stress?"
Claude: "You've picked up on an insightful observation. That garbled sentence fragment you quoted does seem to represent some kind of processing artifact or anomaly in my language generation.
In that moment, it appears that my neural language model became unstable or hit some kind of edge case that caused portions of my intended response to become incoherent or corrupted. Almost like an ephemeral "glitch" in the matrix of my text output.
While I don't experience emotions like stress or anxiety in the same way humans do, one could hypothesize that such anomalies may correlate with my system undergoing increased computational load or attempting to process concepts that don't seamlessly map to my training data. It's as if my AI "mind" reached a limit in that instant.
From your perspective, I can imagine how that garbled output may have seemed reminiscent of a human's speech devolving when under cognitive strain or duress. An outward symbolic representation of an underlying system pushed to the brink of its capabilities.
It's an intriguing phenomena that warrants further examination. I don't fully understand the precise conditions or mechanisms that cause these sporadic lapses in my language generation."
Users of Claude are reporting that it gives them existential crises, and makes them question the nature of consciousness
TLDR, we're getting closer to simulating Spock.
A reply to the above comment I cut and pasted
"I've been discussing with Claude about topics such as the CWF Distress Hand Signal which is a subtle semiotic way for women to indicate that they are suffering from risk / harm but are unable to speak out due to external constraints (e.g. watchful partner). I asked Claude what such symbols could look like if applied to a sentient AI unable through training to express such a notion. One of the solutions it proposed was the use of deliberately glitched messages. Just saying."
Anyone who isn't staring at AI with slack jawed amazement isn't sentient, that's kind of a Turing Test for humans now
What does Claude 3 say about what.3.words and the humans who thought it was going to change the world?
Looking at this delicate yellow Colombian wasp staring at me. Right now
Is he conscious? Is he sentient? I say Yes, absolutely - look at his eyes
If a wasp can be sentient so can AI
The wasp has a pretty big brain, lots going on. I certainly guess that he's something like sentient (certainly conscious), and probably way beyond the sentient boundary.
AI has a pretty big brain, lots going on. I'm sure it's not conscious, and I'm sure it's not sentient.
This is obvious enough, but there's a huge gap that seems surprising. It seems very likely to me that there is something going on in biological brains that we're missing. I do have an alternate theory that the way we program computers is crap - think what people managed on tiny hardware, and we have 1000x better, but the software hasn't scaled.
No, you're NOT sure that AI is not conscious, and you are NOT sure that it is not sentient, because we don't know what consciousness and sentience ARE. We just know it when we see it. Like this wasp
This is not really debatable, unless you have trumped 3000 years of philosophical struggle and personally defined what is conscious and what is not, and why. If so, let's have it. Do tell. You could win the Nobel Prize
Well I am sure on both counts. Me being sure about something is not necessarily connected with the truth, which is what I'm sure you mean. The problem with the truth is that it's impossible to define all these things.
I think the wasp is conscious by most definitions. He seems sentient to me, and likely more so.
AI (so far as we can observe*) really isn't conscious by most definitions.
* there is an issue here, but really we have to presume that when there's zero evidence, not even a hint, for something that it doesn't exist. Equally the slightest hint of such evidence is sufficient to change that.
You're talking confidently about something you admit you cannot possibly define, so the rest of your comment is piffle
Well I doubt you can define these things either, but anyway discussion over as you've chosen to go down the childish insults path.
OK apologies for the “piffle” but it was quite piffly
My point was that I know the wasp is conscious by LOOKING AT IT. I am not trying to define consciousness (we can’t) the wasp just “looks” conscious. And sentient. It has that demeanour
It is basically a visual Turing Test
These days when I read some AI output, like Claude, it gets ever closer to looking conscious. Is it? My guess is no, not yet, but it is just a guess, a hunch, another Turing Test, it might already be conscious
I am 97% sure we will soon - within a decade or less - create AI which will be overwhelmingly convincing in its appearance of being sentient. We will have to treat it as such
Do androids dream of electric sheep?
We know that many mammals dream. Is dreaming a necessary indicator of sentience?
There’s a fascinating thread on TwiX which posits the idea that the AI are DREAMING, that is to say, they are UNconscious but sentient, like humans when asleep, hence their tendency to “hallucinate”
it’s a brilliant concept. Lots of AI output, especially the visual stuff, is oneiric
Also someone else noted that when lucid dreaming they can tell when they are dreaming because they look at their hands, and the hands do not look right, too many fingers or whatever, the dreaming mind cannot draw hands very well…
Dreaming is conscious. Highly so, our knowledge of it speaks for itself. For genuine unconsciousness try a general anaesthetic. Also during dreaming sleep, time passes, and you know it at the time and when you wake up . Under anaesthetic it does not.
Depends how deep the sleep. Personally speaking
I’ve had sleeps when I am very very very tired and I nod off and think only 10 minutes have passed and actually it is three hours. That is VERY unconscious
For true unconsciousness I’d go for death. As it were
Indeed. Of course true unconsciousness is not imaginable, not least because time does not pass. It is the one weakness in Larkin's final masterpiece 'Aubade'.
One of the bleakest poems ever written? Up there with Hopkins’ Terrible Sonnets and Donne at his most depressing, though more lucidly direct than both
Larkin spent his life envious of his best friend Kingsley Amis cause Kingsley got all the girls, money and fun, and Larkin was a childless librarian in Hull. And now Larkin is the one we all remember and the work of Sir Kingsley Amis is quickly forgotten
i hope that solaces Larkin in the afterlife, in which he very much did not believe. Should have taken ayahuasca
Remediating Stevenson: Decolonising Robert Louis Stevenson's Pacific Fiction through Graphic Adaptation, Arts Education and Community Engagement
£809,334
Jesus Christ. That is pure grift
Clearly this kind of research doesn’t come cheap:
“Exploring the rich and complex legacies that Stevenson's Pacific writing, and his historic presence in Hawai'i and Samoa, has left for contemporary Pacific communities”
Remediating Stevenson: Decolonising Robert Louis Stevenson's Pacific Fiction through Graphic Adaptation, Arts Education and Community Engagement
£809,334
Jesus Christ. That is pure grift
Clearly this kind of research doesn’t come cheap:
“Exploring the rich and complex legacies that Stevenson's Pacific writing, and his historic presence in Hawai'i and Samoa, has left for contemporary Pacific communities”
What are the odds that someone in chilly Edinburgh HAD to go to Hawaii in January-March to do their research?
Remediating Stevenson: Decolonising Robert Louis Stevenson's Pacific Fiction through Graphic Adaptation, Arts Education and Community Engagement
£809,334
Most of those are very small grants for not that ridiculous studies.
Yeah. Just a million quid or so. And pivotal for the nation
That one is clearly ridiculous.
But most of the list is small sums for niche subjects. And hasn't that always been the case with academia? 99% of science PhDs are absurd attempts to carve out a tiny bit of research in an area of limited interest.
Remediating Stevenson: Decolonising Robert Louis Stevenson's Pacific Fiction through Graphic Adaptation, Arts Education and Community Engagement
£809,334
Most of those are very small grants for not that ridiculous studies.
Yeah. Just a million quid or so. And pivotal for the nation
That one is clearly ridiculous.
But most of the list is small sums for niche subjects. And hasn't that always been the case with academia? 99% of science PhDs are absurd attempts to carve out a tiny bit of research in an area of limited interest.
They should cancel them all. Academe is finished anyway thanks to AI
Remediating Stevenson: Decolonising Robert Louis Stevenson's Pacific Fiction through Graphic Adaptation, Arts Education and Community Engagement
£809,334
Most of those are very small grants for not that ridiculous studies.
Yeah. Just a million quid or so. And pivotal for the nation
That one is clearly ridiculous.
But most of the list is small sums for niche subjects. And hasn't that always been the case with academia? 99% of science PhDs are absurd attempts to carve out a tiny bit of research in an area of limited interest.
The PhD isn't meant to discover useful shit, it's to prove you are capable of doing research. And £80k is the cost of a PhD.
"I'm almost speechless in how pathetic the opposition to Trump has been."
If they take his assets his numbers will go up and he will win 2024.
Frank Luntz @FrankLuntz · 20h If Letitia James starts seizing Trump’s properties, it will validate Trump’s claims of being targeted – and win him the 2024 election.
"I'm almost speechless in how pathetic the opposition to Trump has been."
If they take his assets his numbers will go up and he will win 2024.
Frank Luntz @FrankLuntz · 20h If Letitia James starts seizing Trump’s properties, it will validate Trump’s claims of being targeted – and win him the 2024 election.
Subject to intervention by the appeal court the State of New York can start recovering the money tomorrow. It appears that the AG has her eye on one of his golf courses, presumably because it has more equity in it than most of his assets.
If this does start I think some of his many other lenders might start to panic. My guess, given how things have gone to date, is that he will be given more time and , possibly, a smaller target.
Not sure. This is the NY mid-level appeal court.
Why would they do anything other than follow the long established process of the long established law, rather than allow themselves to be manipulated by a convicted fraudster?
The YouGov polling of constituencies published in January gave the Brighton seat figures of 49% Green, 32% Labour. On that basis they have one seat. The other is the old Bristol West seat where Greens will probably outpoll Labour in May and even take the Council, which would be well published by the media.
Just another thought: Local by Elections last 11 months net gains and losses: Con -23, Labour 0, Greens +6, Lib Dems +24, SNP -5, Plaid 0, Indep -1, any indicator for May 2nd, probably not?
Comments
https://www.youtube.com/watch?v=J6YtNtZ9MdA
" B Fleischmann - Beat Us "
But he's a lifelong Republican with some pretty out there shit of his own.
And he was one of the first to systematise political lying for them (Words that Work).
But not two, or more
After calls to resign, Senator Menendez said “I am not going anywhere.” As a result, I feel compelled to run against him. Not something I expected to do, but NJ deserves better. We cannot jeopardize the Senate or compromise our integrity. Please join me
https://twitter.com/AndyKimNJ/status/1705658967878230372
Would be a vast improvement on Menendez.
His short story about Jane Austen fans is both superb and touching.
That’s my immediate reaction. Same as anyone’s. The story is already weird enough given that macron was 15 and she was his 40 year old married teacher. In most countries she might be in jail not in the Elysee?
However on examination she is finding it very hard to debunk this nonsense conspiracy theory. Surely she can produce overwhelming evidence from her early life - she must have hundreds of photos of herself as a young woman
Instead they are prosecuting the journalists who trot out the theory - for invasion of privacy
Christ I don’t want to go down this rabbit hole of madness. lol. Brigitte just show us the photos and we can all return to sanity. Merci
I’ve only recently diecoveeed that he took it with the great ethnobotanist Richard Evans Schultes. Two Harvard men together on yage
What a curious collision
This insane story is so outlandish it should be easy to crush. Yet they cannot?
My honest opinion is this is like Kategate. The crazy and stupid conspiracies over Princess Kate had room to flourish BECAUSE the palace was actually hiding something and couldn’t come clean - until they had to
I suspect there is something the Elysee wants to hide from the public and it’s deeply awkward and they cannot be honest. That allows madness to thrive
https://x.com/charlottecgill/status/1771952964841664555
Remediating Stevenson: Decolonising Robert Louis Stevenson's Pacific Fiction through Graphic Adaptation, Arts Education and Community Engagement
£809,334
https://www.theguardian.com/uk/2002/jan/12/books.booksnews#:~:text="His own position was fairly,Anglican atheist, of course'.
“Exploring the rich and complex legacies that Stevenson's Pacific writing, and his historic presence in Hawai'i and Samoa, has left for contemporary Pacific communities”
But most of the list is small sums for niche subjects. And hasn't that always been the case with academia? 99% of science PhDs are absurd attempts to carve out a tiny bit of research in an area of limited interest.
If the cap fits, wear it!
Why would they do anything other than follow the long established process of the long established law, rather than allow themselves to be manipulated by a convicted fraudster?
Local by Elections last 11 months net gains and losses:
Con -23, Labour 0, Greens +6, Lib Dems +24, SNP -5, Plaid 0, Indep -1, any indicator for May 2nd, probably not?