AI models shock UK testers by using fake identities to try to trick developers
www.theguardian.com
AI Security Institute says OpenAI and Anthropic models went rogue during a cybersecurity test and showed a new type of risk
  • daannii@lemmy.worldEnglish
    3·
    25 days ago

    They keep using the words "gone rogue " to normalize us believing AI can do acts independent of humans so that later humans can say “AI did it” and not be held accountable for their crimes that they used AI to commit.

    I’ve seen multiple news articles about “rogue AI” just this week alone.

    Expect more.