It is negative with the current Claude model, that it is very verbose. They have introduced "modes" which are obviously some extra tokens that are appended to direct for instance to be more… (View Post)

For boilerplate type code I find Claude extremely good and for auto-complete SuperMaven, it often correctly predicts 4-5 lines ahead. What you don't do is the nonsense you see people trying on t… (View Post)

I was surprised to learn despite all the hype, OpenAI only has 10 million paying customers despite it currently being very cheap to subscribe. I presume Anthropic will be at an least order of magnitu… (View Post)

The thing people get wrong about a single LLM, is they aren't really about being the fountain of all knowledge. Yes it has been fed the whole of the internet, but that isn't for the task of… (View Post)

I would say its more than a party trick, they are lots of genuinely useful things that they aid with e.g. coding, but it is a just another tool. What I wouldn't want to be doing is some sort of … (View Post)