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 to release Astra, its first model with critical cyber capabilities(7 posts)→

Original post →

More from Models

Models channel →