MCasq_qsaCJ_234@lemmy.zip to Technology@lemmy.worldEnglish · 1 day agoAI is learning to lie, scheme, and threaten its creators during stress-testing scenariosfortune.comexternal-linkmessage-square20fedilinkarrow-up1152arrow-down151
arrow-up1101arrow-down1external-linkAI is learning to lie, scheme, and threaten its creators during stress-testing scenariosfortune.comMCasq_qsaCJ_234@lemmy.zip to Technology@lemmy.worldEnglish · 1 day agomessage-square20fedilink
minus-squarewizardbeard@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up6arrow-down1·23 hours agoYeah. Anthropic regularly releases these stories and they almost always boil down to “When we prompted the AI to be mean, it generated output in line with ‘mean’ responses! Oh my god we’re all doomed!”
Yeah. Anthropic regularly releases these stories and they almost always boil down to “When we prompted the AI to be mean, it generated output in line with ‘mean’ responses! Oh my god we’re all doomed!”