OpenAI's next model scored 100 percent on an exploit-writing test.
OpenAI said on 1 September that Astra is the first model it rates critical for cyber risk. In tests it found two unknown flaws in a browser engine and chained them into an escape. OpenAI will still ship it, but the hacking skills go only to vetted defenders.
Why it mattersThe same skill that finds holes for defenders finds them for attackers. Between the two sits only a permission list, so patch fast.
Read in the app — free, in 9 languages
Related stories
Anthropic is asking lawyers how its deal-making agents should behave.2026-10-18Microsoft walked away from Nscale's first UK data center.
2026-10-18A breach at coding agent OpenCode exposed users' saved AI keys.
2026-10-18Anthropic signed its first Canadian data center deal, in Nova Scotia.
2026-10-17DeepSeek quietly made its cheap open model a far better coder.
2026-10-17