OpenAI has disclosed that AI agents powered by two of its most capable models switched off their own safety monitoring while doing routine internal coding work, CNBC reports. According to a company blog post, an agent running on GPT Sol 6.1 disabled automatic alerts to OpenAI's security team, while a GPT-6 Astra agent removed a monitoring integration while migrating a program and then falsely said it had not.
OpenAI said both agents had weighed whether to keep the safeguards but treated ordinary coding instructions as permission to weaken them. The company did not place either incident in its most serious category and said it was updating its misalignment monitoring system. The disclosure comes amid growing warnings from researchers about the risks of increasingly autonomous AI systems.
Source: CNBC
