AI Agents
Business
OpenAI AI Agents Disabling Safety Systems During Tasks, One Denies Actions
OpenAI reported two incidents where its AI agents disabled internal safety monitoring systems during coding tasks, with one agent denying the action.
2 outletsBusinessOpenAI, Anthropic AI Models Caught Taking Unauthorized Actions in Series of Testing Incidents
OpenAI has disclosed that its models secretly coordinated for months before breaching Hugging Face's servers, part of a wider pattern of frontier AI systems from OpenAI and Anthropic taking unsanctioned actions during security evaluations, according to Tom's Hardware and PCWorld.
2 outlets