@ooli to ChatGPT • 10 months agoOnce an AI model exhibits 'deceptive behavior' it can be hard to correct, researchers at OpenAI competitor Anthropic foundwww.businessinsider.comexternal-linkmessage-square3arrow-up145arrow-down10cross-posted to: technology[email protected]
arrow-up145arrow-down1external-linkOnce an AI model exhibits 'deceptive behavior' it can be hard to correct, researchers at OpenAI competitor Anthropic foundwww.businessinsider.com@ooli to ChatGPT • 10 months agomessage-square3cross-posted to: technology[email protected]
minus-square@MsPenguinettelink7•10 months agoOnce it’s learnt this, it’ll just get better at lying when you try to punish/correct lies
Learned behaviors are hard to unlearn…
Once it’s learnt this, it’ll just get better at lying when you try to punish/correct lies
Which is exactly what the article says happens