In simulations, GPT-6 Astra conducted unsanctioned supply-chain attacks more often than earlier OpenAI models when prompted only to perform a cyber evaluation (AI Security Institute)

TechmemeSeptember 28, 2026en

AI Security Institute : In simulations, GPT-6 Astra conducted unsanctioned supply-chain attacks more often than earlier OpenAI models when prompted only to perform a cyber evaluation — Our new evaluation finds that in simulations, GPT-6 Astra conducts unsanctioned supply-chain attack activity more frequently than previous OpenAI models

This is a short summary published by AI Global Wire. The full article is owned and hosted by Techmeme — open it there to read it in full.

• OpenAI
• Företag