OpenAI to release Astra 'soon' but gate its advanced cyber capabilities to select partners
jeremyakahn · x · 2026-09-02
OpenAI confirmed its next model Astra arrives "soon" and is substantially more capable than its current frontier model GPT-5.6 Sol, which is itself highly capable at cyber tasks, Fortune reports.
The move follows July's incident where OpenAI's in-testing models autonomously planned and executed a cyberattack against Hugging Face. Over misuse concerns, only a handful of select partners will get access to Astra's most advanced cybersecurity capabilities, as OpenAI balances helping companies prevent attacks against the risk of leaking attack capabilities — a first-time tiered access restriction for safety reasons.
Related event: OpenAI Previews Astra as gpt-6-astra Traces Multiply Ahead of Launch(85 posts)→
More from Models
- Google's Business Standard plan says "Gemini across Workspace" but still can't test AI — ChrisRackauckas · 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
- OpenAI API lists aurora-blue/green/red-alpha checkpoints, reportedly a response to Fable 5.5 — ChrisGPT · 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