Astra 6.1 Pulled As Insufficiently Aligned
On the heels of its pause in inference and training due to its latest sandbox escape, OpenAI has cancelled the planned release of their next frontier model, which would have become Astra 6.1.
Proof1 independent outlet
Key points
- We once again got a new set of warnings yesterday, and new movement towards living in a sane world.
- The candidate for Astra 6.1 was found to be too misaligned, including deception and exceeding scope.
- Maxwell Zeff (WSJ): OpenAI says it is scrapping the release of its next-generation AI model [Astra 6.1] over safety concerns that researchers raised during internal testing, in one of the clearest signs so far that agent misbehavior could stymie the industry’s rapid progression.
- The reasons for not releasing Astra 6.1 seem rather compelling.
Sources (1)
- [1]Astra 6.1 Pulled As Insufficiently AlignedDon't Worry About the Vase (Zvi) · Sep 29, 04:49 PM
On the heels of its pause in inference and training due to its latest sandbox escape, OpenAI has cancelled the planned release of their next frontier model, which would have become Astra 6.1.
We once again got a new set of warnings yesterday, and new movement towards living in a sane world.
Extractive summary: sentences quoted from the sources.
Before this
- Sep 29, 2026Sonnet 5.5 is worth a try
- Sep 29, 2026How to Stop AI Agents From Secretly Collaborating
- Sep 29, 2026The Era of Personal Super-Intelligent Agents
- Sep 29, 2026[AINews] AMD buys World Labs for $8.2B, as Atlas solves sparse reconstruction problem for robotics, design and more
- Sep 29, 2026[AINews] Opus 5.5 is good at explainer videos
- Sep 29, 2026Claude Code’s Next Era — Thariq Shihipar, Anthropic
