mediocreatbest@lemmy.sdf.orgM to mediocreatbest@lemmy.sdf.orgEnglish · 3 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-square0linkfedilinkarrow-up11arrow-down10cross-posted to: math@lemmy.sdf.org
arrow-up11arrow-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.orgmediocreatbest@lemmy.sdf.orgM to mediocreatbest@lemmy.sdf.orgEnglish · 3 years agomessage-square0linkfedilinkcross-posted to: math@lemmy.sdf.org
