"This is not just hallucinations. There's a very strategic kind of deception."
  • wizardbeard@lemmy.dbzer0.comEnglish
    71·
    6 个月前

    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!”