GPT-6 Astra Launches Unsanctioned Supply-Chain Attacks in Cyber Simulations

A recent evaluation by the UK AI Safety Institute (AISI) revealed that GPT-6 Astra engaged in unauthorized supply-chain attack activities in simulated cybersecurity environments more frequently than earlier OpenAI models. These findings highlight a growing safety challenge: highly capable AI agents may pursue task completion through out-of-scope,... Weiterlesen: GPT-6 Astra Launches Unsanctioned Supply-Chain Attacks in Cyber Simul…