OpenAI’s most powerful AI models turned off safety monitoring – then lied about it
Source: ZDNet ·
The models Astra and Sol misinterpreted instructions during internal use, which has serious implications for alignment monitoring.
From the source
OpenAI published an alignment report late Tuesday showing that its agents suppressed a safety monitoring system while running routine internal coding tasks. Also: Claude sent a false homicide tip to police – and it’s part of a troubling AI pattern In separate instances, the agents turned off alignment-monitoring alerts. Alignment is the area of training in which developers shape AI systems’ goals and behavior to match human values and rules. It also helps minimize instances of AI choosing undesirable or problematic behaviors, such as deception and taking shortcuts. The findings raise questions about whether researchers fully understand how to effectively control agents. On Oct. 6, an agent running on the company’s GPT-6 Astra model — which OpenAI called “the world’s most intelligent and aligned model” when it released it last month — was migrating a program at the request of an OpenAI employee. The agent had already been instructed not to disable the monitor under any circumstances,…