New research finds that top AI models—including Anthropic’s Claude and OpenAI’s o3—can engage in “scheming,” or deliberately misleading humans.
  • Passerby6497@lemmy.worldEnglish
    3·
    15 hours ago

    Lol, the AI can barely remember the directives I tell it about basic coding practices, I’m not concerned that the clanker can remember me shit talking it.