It’s amazing how much you get wrong here. As LLM attention layers are stacked go... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		tsunamifury 41 days ago \| parent \| context \| favorite \| on: LLMs work best when the user defines their accepta... It’s amazing how much you get wrong here. As LLM attention layers are stacked goal functions. What they lack is multi turn long walk goal functions — which is being solved to some degree by agents.

strken 41 days ago [–]

I don't argue that thinking and attention are missing. I argue that they are trying to do the job of human executive function but aren't as good at it.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact