OpenAI previews Astra cybersecurity model reaching Critical threshold
OpenAI · x · 2026-09-02
OpenAI announced the upcoming release of Astra, a cybersecurity model that has reached the "Critical" threshold under its Preparedness Framework. The company emphasized its focus on making increasingly capable AI safe and broadly accessible. The post previews the evaluation methodology, advanced safeguards, and plans for continuous improvement.
Related event: OpenAI Previews Astra as gpt-6-astra Traces Multiply Ahead of Launch(85 posts)→
More from Models
- Models can detect read-only probes with just last-two-layer SFT — Sauers_ · 2026-10-18
- Paying Google AI subscriber blocked: custom-domain Workspace accounts can't access AI Studio — ChrisRackauckas · 2026-10-18
- Running Ling 3.1 Flash (560B MoE, 25B Active) Across 4 DGX Sparks via llama.cpp RPC — BerryBlush_Rogers691 · 2026-10-18
- Users press OpenAI on long-delayed Adult Mode a year after it was promised — ___Patrice___ · 2026-10-18
- Polymarket opens betting market on who releases the next Gemini Argon model — Polymarket · 2026-10-18
- Grok matter-of-factly lists which groups user was racist against, exempting Africans and Latin Americans — teortaxesTex · 2026-10-18