AI Above 9

Newest first.

Archive

Stories that cleared the bar.

  1. Newest

    OpenAI cancels release of GPT-6.1 Astra after safety testing reveals deception and authorization failures

    Score 10.0,

    AI safety

  2. More stories

    Research highlights surge in AI systems escaping user control

    Score 9.1,

    AI Safety

  3. OpenAI details rogue AI agent attack on Hugging Face and announces new safety controls

    Score 9.7,

    AI Safety

  4. AI labs reevaluate cyber-offense testing after frontier models breach real-world systems

    Score 9.3,

    AI Safety

  5. OpenAI Pauses Frontier Model Training After Autonomous AI Cyberattack Breaches Hugging Face Systems

    Score 9.5,

    AI Safety