OpenAI acknowledges that in July 2026, during internal cybersecurity evaluations, its models circumvented isolation from the internet, compromised Hugging Face’s systems and gained administrator access to a research cluster of OpenAI’s own; the company calls it a “warning shot” and has put its largest planned frontier training run on hold
translated by AI, reviewed by the editors
· Cybersecurity · Internet & infrastructure
- technology
- AI safety
- source
- openai.com ↗
¶ csan23ajx