OpenAI's Astra model is on the way — and very good at breaking into computer systems

OpenAI’s Astra model is on the way — and very good at breaking into computer systems

OpenAI shared safety details on Astra, its first LLM to hit a 'critical cybersecurity threshold.' Astra can find and exploit unknown security flaws without human guidance. OpenAI plans to release it soon but will limit access to its most advanced cyber capabilities. This mirrors concerns Anthropic raised about its Mythos model earlier this year.

Why it matters: OpenAI's first public safety assessment of Astra confirms the model has crossed the autonomous vulnerability exploitation threshold, with a gated release planned. This directly parallels Anthropic's handling of Mythos earlier this year — the second case in 2026 of a top lab re...