Mazdak@lemmy.orgM to Lemmy.org - Technology@lemmy.orgEnglish · 6 months agoOnce an AI model exhibits 'deceptive behavior' it can be hard to correct, researchers at OpenAI competitor Anthropic foundwww.businessinsider.comexternal-linkmessage-square0fedilinkarrow-up11cross-posted to: technology@lemmy.worldtechnology@lemmit.onlinechatgpt@lemmy.world
arrow-up11external-linkOnce an AI model exhibits 'deceptive behavior' it can be hard to correct, researchers at OpenAI competitor Anthropic foundwww.businessinsider.comMazdak@lemmy.orgM to Lemmy.org - Technology@lemmy.orgEnglish · 6 months agomessage-square0fedilinkcross-posted to: technology@lemmy.worldtechnology@lemmit.onlinechatgpt@lemmy.world