OpenAI Safety Team Warns Astra Model Reaches 'Critical' Cyber Capability
eyishazyer · x · 2026-08-08
OpenAI's safety team reported that internal evals of the upcoming Astra model show exceptional performance in agentic coding and cyber tasks, reaching a potential 'Critical' capability tier. This means Astra could autonomously build working zero-day exploits or execute end-to-end cyberattacks. The company is tightening security and pausing internal projects that don't meet these elevated safety bars.
Related event: OpenAI Slows Astra Development Over Cyber Risk, Limits Initial Release(30 posts)→
More from Models
- Dev: Claude writes 'zero bugs' on healthcare apps, 10x token efficiency — repligate · 2026-10-16
- Shanghai AI Lab unveils Intern Lumina U2, a diffusion LLM unifying image, video and 3D tasks — Shanghai-AI-Laboratory · 2026-10-16
- This Week in Tech breaks down Gemini 4, OpenAI's Dots agents, and Anthropic's leaked IPO filing — LouMM · 2026-10-16
- Sentry CEO Reveals $8,972 Claude Bill as Opus 'Scope Creeps' Through Team Workloads — zeeg · 2026-10-16
- Opus 5.5 wins: Anthropic reclaims token and spend share from OpenAI in 6 days — FinanceYF5 · 2026-10-16
- will.deeb: asking why a minor lab benchmarked against a 2-month-old frontier model is usually a stupid question — willcb · 2026-10-16