themachinestops@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · edit-218 days ago'I had to RUN to my Mac mini like I was defusing a bomb': OpenClaw AI chose to 'speedrun' deleting Meta AI safety director's inbox due to a 'rookie error'www.pcgamer.comexternal-linkmessage-square165linkfedilinkarrow-up1568arrow-down123file-text
arrow-up1545arrow-down1external-link'I had to RUN to my Mac mini like I was defusing a bomb': OpenClaw AI chose to 'speedrun' deleting Meta AI safety director's inbox due to a 'rookie error'www.pcgamer.comthemachinestops@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · edit-218 days agomessage-square165linkfedilinkfile-text
minus-squareTBi@lemmy.worldlinkfedilinkEnglisharrow-up2arrow-down1·18 days agoYeah. Like they are trying to show the AI is more powerful than it is. I don’t use AI that much, does this use case actually happen? Where the AI does something then apologises?
minus-squarexep@discuss.onlinelinkfedilinkEnglisharrow-up6·18 days agoLLMs will often respond in a reconciliatory or obsequious manner when presented with confrontational input.
Yeah. Like they are trying to show the AI is more powerful than it is.
I don’t use AI that much, does this use case actually happen? Where the AI does something then apologises?
LLMs will often respond in a reconciliatory or obsequious manner when presented with confrontational input.