New research finds that top AI models—including Anthropic’s Claude and OpenAI’s o3—can engage in “scheming,” or deliberately misleading humans.
  • ExLisperAEnglish
    1·
    2 months ago

    So you think Gemini told you the truth here? How do you know it’s not just scheming?

    • itisileclerk@lemmy.worldEnglish
      1·
      2 months ago

      Ask Gemini about genocide in Gaza. Deffinetly not truth, watering down IDF’s war crimes like “unconfirmed”.

      • ExLisperAEnglish
        1·
        2 months ago

        Yeah, but why ask Gemini about it’s priorities? I can just lie about it.