Taming AI Bots: Prevent LLMs from entering "bad" states using continuous guidance from the LLM ("is this good? bad?") to avoid bad states.

1 crossposts

math @lemmy.sdf.org goosethe @lemmy.sdf.org 1 yr. ago

Taming AI Bots: Prevent LLMs from entering "bad" states using continuous guidance from the LLM ("is this good? bad?") to avoid bad states.

arxiv.org /pdf/2305.18449.pdf