Why would you deprive the LLM of a signal that indicates how badly it screwed up?
Because it's a completion engine and has no notion of "signals".
Swearing was in the texts they were trained on to complete token by token. I suspect it weren't texts with a lot of high-quality reasoning.
alt Hacker News
Because it's a completion engine and has no notion of "signals".
Swearing was in the texts they were trained on to complete token by token. I suspect it weren't texts with a lot of high-quality reasoning.