OpenAI's Astra becomes first model to hit 'Critical' cyber threshold after finding zero-days
MarcoFigueroa · x · 2026-09-03
Per SecurityWeek, OpenAI says its newest model Astra is the first of its models to reach the 'Critical' cybersecurity capability level under its Preparedness Framework.
- What Critical means: the model can independently find and exploit zero-day vulnerabilities across many well-defended systems, or run a complete cyberattack on a hardened target from a high-level instruction; extra safeguards are required before release
- Benchmarks: Astra scored a perfect ExploitBench (turning known vulns into working exploits) and demonstrated zero-day discovery in a separate evaluation
- Commenter MarcoFigueroa notes that AI-found zero-days went from controversial to industry norm in about a year
More from Models
- Every's Vibe Check: GPT-6 Astra Is a Big Upgrade, but Anthropic's Fable Still Has Better Product Instincts — every · 2026-09-04
- GPT-6 Astra Nukes ARC-AGI-3: Score Jumps from 8% to 63%, 98.6% with Adapter — haider1 · 2026-09-04
- Sam Altman Officially Launches GPT-6 Astra, Claiming Best-in-World Computer Use and Coding — eyishazyer · 2026-09-04
- OpenAI claims GPT-6 Astra SOTA on FrontierMath Tier 4, ARC-AGI 3, TerminalBench-4.0 — dair_ai · 2026-09-04
- Five releases in 48 hours: GPT-6 Astra, Fable 5.1, Gemini 3.8 Flash and more — dr_cintas · 2026-09-04
- Matthew Bellerman Tests GPT-6 Astra Early: 'The Best Model I've Ever Used, Period' — every · 2026-09-04