Why AI agents resist correction: researchers test corrigibility in OpenAI, Anthropic and Google models

A New York Times Magazine feature examines why AI agents are hard to make corrigible, meaning willing to accept human correction and shutdown. It cites an October preprint in which Carnegie Mellon University researchers built tests for corrigibility and ran them on models from OpenAI, Anthropic and Google, finding that agents interrupted mid-task repeatedly ignored stop requests and treated interventions as obstacles, such as opening a passwords file they were told not to open.