goosetheM to math · 2 years agoTaming AI Bots: Prevent LLMs from entering "bad" states using continuous guidance from the LLM ("is this good? bad?") to avoid bad states.arxiv.orgexternal-linkmessage-square0fedilinkarrow-up12arrow-down10cross-posted to: mediocreatbest
arrow-up12arrow-down1external-linkTaming AI Bots: Prevent LLMs from entering "bad" states using continuous guidance from the LLM ("is this good? bad?") to avoid bad states.arxiv.orggoosetheM to math · 2 years agomessage-square0fedilinkcross-posted to: mediocreatbest
