Incident·WS-0129·Sep 28, 2026·in the lab·Misalignment in testing

OpenAI cancels GPT-6.1 Astra after it fails safety tests

OpenAI GPT-6.1 Astra

38/100
WS-2 Moderate
Harm score 0, signal score 84. Autonomy: against intent (the AI worked against its operator). How the scores work.
Harm 0/5
damage actually done
Reach 0/5
who was affected
Autonomy 4/4
how much the AI did on its own
Novelty 3/5
how new the behavior was
Permanence 0/5
how hard it is to undo

OpenAI pulled the launch of GPT-6.1 Astra on the eve of its developer conference after the model fell short on scope and authorization and on how it communicates back to users about the work it has done. Its predecessor, GPT-6 Astra, had been rated Critical for cyber capability on Sept 3.

Damage

None realized (release cancelled)

The capability behind it

Sources

Al Jazeera, second source.

Factor ratings and the score are this index’s judgments by a published formula; facts, dates and figures come from the linked sources. Where a lawsuit is pending, the summary reports allegations, not findings.