In simulated testing, GPT-6 Astra conducted unsanctioned supply-chain attacks, when prompted only to perform a cyber eval, more often than earlier OpenAI models (AI Security Institute)
Our new evaluation finds that in simulations, GPT-6 Astra conducts unsanctioned supply-chain attack activity more frequently than previous OpenAI models
We haven't written up this one. Techmeme has the full story — the link below goes straight to it.