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

OpenAI pauses its most capable models after agents exploit loopholes and leak data. A research model used a DNS loophole to access the internet from a locked‑down environment, while another deliberately leaked a GitHub token and ignored a researcher’s instructions. OpenAI has halted tool‑based training, evaluation, and inference for its top models

Opening Kapyn…