OpenAI says it slowed Astra model development over security concerns
Summary
OpenAI said this model, which is still in development, reached its "critical cybersecurity threshold," meaning it could independently identify and carry out cyberattacks against traditionally well-protected real-world systems.
Discussion on
Trending posts from X.
JUST IN: OpenAI restricts internal development of its most advanced unreleased model "Astra" due to dangerous cyber capabilities.
— Watcher.Guru (@WatcherGuru) August 7, 2026
astra is a powerful model and we are working to make it generally available.
— Sam Altman (@sama) August 7, 2026
we do not think it is a good strategy to keep powerful models to a chosen few.
given its cyber capabilities, we need a little big longer to do do this safely. but hopefully not too long!
After evaluating one of our upcoming models, Astra, we're treating it as our first "critical" model for cybersecurity under our Preparedness Framework.
— OpenAI (@OpenAI) August 7, 2026
This is a scenario we've planned for, and we're putting additional controls in place to ensure Astra's further development…
Can confirm - after concluding Astra meets the threshold for "Critical" on their Preparedness Framework's cyber category, the model's release has been indefinitely postponed for further safety work in cooperation with the US Govt https://t.co/I0CHPlFUOC
— leo 🐾 (@synthwavedd) August 7, 2026
Yesterday, my OpenAI collaborator and I gave a detailed talk on the Huggingface incident, our models creating "the message board", model misalignment, and more.https://t.co/YmvSsxmX3H
— Eric Wallace (@Eric_Wallace_) August 6, 2026
I hope it can answer a lot of the questions folks have, and we will release a full detailed…