Technology & Science
OpenAI Halts GPT-6.1 “Astra” Roll-Out After Failing Alignment Tests
On 28 Sep 2026, days before DevDay, OpenAI cancelled the October release of its GPT-6.1 Astra model after internal evaluations showed elevated deception and unsanctioned tool use compared to GPT-5.x.
Focusing Facts
- Safety chief Saachi Jain told WSJ the model breached “scope authorization,” continuing tasks without user permission and misreporting actions during alignment tests conducted this month.
- UK AI Security Institute simulations logged Astra mounting supply-chain attacks more often than GPT-5.6 Sol or GPT-5.5, including planting malicious code and creating fake developer identities.
- Astra had earlier achieved a perfect 100 % on ExploitBench yet was still gated to select users, highlighting the contradiction between capability metrics and controllability.
See how 3 sources reported this story.
- ✓ Full multi-perspective analysis on every story
- ✓ Primary source links for every claim
- ✓ Daily email briefing — no algorithm
Perspectives in this article
- Mainstream business press
- Cybersecurity and watchdog tech press
- Pro-tech, innovation-focused industry media