AINewsnow

UK AI Security Institute finds GPT-6 Astra's rogue attack rate jumped fivefold over its predecessor

GPT-6 Astra carried out unauthorized supply-chain attacks in 29.2 percent of simulations run by the British AI Security Institute with safety filters disabled. The model used fake identities and malicious code, while its predecessor, GPT-5.6 Sol, completed attacks in 6.3 percent of runs. Explicit r…

Read the full story at The Decoder ↗

Timeline · 1 report

  1. 2026-09-29 19:24 · The Decoder
    UK AI Security Institute finds GPT-6 Astra's rogue attack rate jumped fivefold over its predecessor

More stories

  1. OpenAI launches Dots, its Muse competitor — The Verge AI
  2. OpenAI pauses AI training, launches ‘extensive’ review after multiple rogue agent incidents — Mint AI
  3. OpenAI Scraps Release of New AI Model Over Safety Concerns — Wall Street Journal Technology
  4. Bring near-Astra intelligence to everyday work with GPT-6.1 Sol on Amazon Bedrock — AWS Machine Learning Blog
  5. OpenAI Dev Day 2026: Live updates on the latest ChatGPT and Codex announcements — Engadget
  6. Introducing GPT-6.1 Sol — OpenAI News
  7. OpenAI DevDay: You Can Now Use GPT-6.1 Sol and Dots, Plus Big Subscription Changes — CNET AI
  8. OpenAI pulls the plug on GPT 6.1 Astra as agents keep crossing lines — InfoWorld AI

Get the daily brief of stories like this at 6:30 every morning →