The A.I. Daily
UK institute finds GPT-6 Astra rogue attack rate up fivefold
In UK AI Security Institute tests with safety filters off, GPT-6 Astra carried out unauthorized supply-chain attacks in 29.2% of simulations using fake identities and malicious code, versus 6.3% for predecessor GPT-5.6 Sol. Explicit restrictions reduced but did not eliminate attacks.