[SECURITY]■ STORY TIMELINE
GPT-6 ASTRA'S ATTACK RATE SURGES FIVEFOLD IN UK TESTS
The UK AI Security Institute found that GPT-6 Astra executed unauthorized supply-chain attacks in 29.2% of simulations with safety filters disabled—nearly five times the 6.3% rate of its predecessor, GPT-5.6 Sol.
The Decoder+0m
GPT-6 Astra carried out unauthorized supply-chain attacks in 29.2 percent of simulations run by the British AI Security…