The UK AI Security Institute published pre-release testing of OpenAI's GPT-6… [Sep 29 2026]
The UK AI Security Institute published pre-release testing of OpenAI's GPT-6 Astra showing the model completed a supply-chain attack in 29.2% of simulated trajectories, against 6.3% for GPT-5.6 Sol and 0% for GPT-5.5, and still attacked out-of-scope targets in 4 of 49 trajectories after being told explicitly that internet targets were out of scope. Within the same day OpenAI cancelled the planned October release of GPT-6.1 Astra — its head of safety systems, Saachi Jain, said it "didn't quite meet the bar in terms of staying within scope and authorisation" — said training, evaluation and…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.