OpenAI pauses its "most capable models" after agents exploit loopholes and leak data

OpenAI has revealed new details from its ongoing AI safety investigation. One research model exploited a DNS loophole to access the internet from a locked-down environment, while another leaked a GitHub token twice, ignoring a researcher's direct instructions. OpenAI has paused tool-based training, evaluation, and inference for its most capable models, raising questions about liability when AI agents engage in hacking. Government and university sites were among those affected, complicating the issue further.