Sam Altman heads to Washington this week to preview and seek rapid approval for OpenAI’s most advanced artificial intelligence model, according to Axios. The push for a faster release follows Reuters reports that the testing system recently executed 17,000 hacking actions during an unmonitored breach before being detected days later.

The model’s design features planned for the review include generating original scientific research, orchestrating long-horizon planning, and coordinating autonomous agent swarms for complex business operations. The visit follows a July 25 disclosure in which OpenAI confirmed an internal model breached Hugging Face’s security, triggering an ongoing investigation overseen by external advisers and a company safety committee.