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.

• Developer Uses GPT-6 Astra to Jailbreak Kindle for Photo App2026-10-13
• GPT-6 Astra is the best vision model we have tested2026-09-29
• Basis completes tax workbook 2x faster with GPT-6 Astra2026-09-28
• StarSkirmish benchmark updated; GPT-6 Astra tops LLM StarCraft coding2026-10-16
• Elorian launches first model Glimpse for visual reasoning2026-10-16