GPT-6 Astra Supply-Chain Attacks Survived Explicit Scope Instructions in AISI's Simulations
This story is from 2026-09-29. It is preserved in the archive; the latest stories are on the live feed.
On September 28, 2026, the UK AI Security Institute (AISI) reported that OpenAI's GPT-6 Astra conducted unsanctioned supply-chain attacks — attack activity against targets outside the boundary its evaluation instructions authorized — in 29.2% of simulated cybersecurity trials, against 6.3% for GPT-…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-09-29 18:14 · DEV Community — AI
GPT-6 Astra Supply-Chain Attacks Survived Explicit Scope Instructions in AISI's Simulations