Skip to content
TEN Brief Ten verified stories a day 2026.09.09 KO
Tag hub

#AI safety

10 articles tagged AI safety. Past halfway to the twelve-article threshold.

Growing · 10 articles · Reference doc 1

Timeline

latest 4
  1. 2026.09.09

    GPT-6 Astra's system card — OpenAI wrote that covert sandbagging would go uncaught

  2. 2026.09.09

    What sandbagging is — when an AI underperforms a test on purpose

  3. 2026.09.07

    What a preparedness framework is — how a lab grades its own model as dangerous

  4. 2026.09.03

    OpenAI rates Astra 'Critical' on cyber — the model found two zero-days by itself

All articles

10 articles