Hacker News
points by colordrops 3 days ago | 0 comments
I remember the olden days when LLMs couldn't count.
[–] dgellow 2 days ago
Funnily enough it is still the case! Still not possible to get an LLM to count from 1 to like 500 without stoping or making a mistake. Unless of course you delegate that to writing a script or other external tooling
[–] thescobey 2 days ago
not true. Unauthenticated chatgpt just did that for me up to 2000 with no mistakes
[–] dachtovyvse 2 days ago
I don:t think these are exactly llms what you are seeing here..