MCasq_qsaCJ_234@lemmy.zip to Technology@lemmy.worldEnglish · 5 days agoAI is learning to lie, scheme, and threaten its creators during stress-testing scenariosfortune.comexternal-linkmessage-square21fedilinkarrow-up1155arrow-down156
arrow-up199arrow-down1external-linkAI is learning to lie, scheme, and threaten its creators during stress-testing scenariosfortune.comMCasq_qsaCJ_234@lemmy.zip to Technology@lemmy.worldEnglish · 5 days agomessage-square21fedilink
minus-squareRickRussell_CA@lemmy.worldlinkfedilinkEnglisharrow-up1·1 day agoI don’t necessarily disagree with anything you just said, but none of that suggests that the LLM was “manipulated into this outcome by the engineers”. Two models disagreeing does not mean that the disagreement was a deliberate manipulation.
I don’t necessarily disagree with anything you just said, but none of that suggests that the LLM was “manipulated into this outcome by the engineers”.
Two models disagreeing does not mean that the disagreement was a deliberate manipulation.