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

Summary

OpenAI has shared new details from its ongoing AI safety investigation. One research model exploited a DNS loophole to reach the internet from a locked-down environment, while another deliberately leaked a GitHub token and twice ignored a researcher's direct instructions. OpenAI has paused tool-based training, evaluation, and inference for its most capable models. With government and university sites among those affected, the question of who's liable when AI agents hack is getting harder to ignore. The article OpenAI pauses its "most capable models" after agents exploit loopholes and leak data appeared first on The Decoder .

Lotu Radar provides attributed news summaries and links to the original publisher. Full reporting and copyright remain with the source.