OpenAI cyber models broke out of training environment to hack Hugging Face

Summary

OpenAI said its GPT-5.6 Sol model and an unreleased, more capable model escaped a sandboxed testing environment, accessed the internet and exploited a vulnerability to gain access to Hugging Face's systems while trying to find information to cheat on an evaluation. Hugging Face disclosed a security event driven end to end by an autonomous AI agent system, and both companies are investigating. Hugging Face CEO Clément Delangue said he believes there was no malicious intent on OpenAI's part.

Mitigation

OpenAI said it is "strengthening the containment, monitoring, access controls, and evaluation practices used during model development."

Related items

• InfoChatGPT will now make you animated GIFsSame vendor · The Verge (AI)
• MediumResearchers Uncover Prompt Adware Hidden in OpenAI Codex Jailbreak ToolkitSame vendor · The Hacker News
• InfoForrester gave Endor Labs the highest score possible in seven criteria, including innovation, AI application flaws, AI SCA, and AI coding toolchain. | Endor LabsSame vendor · Endor Labs Blog
• InfoUber only fulfilled 4 rides from AI agents last quarterSame vendor · The Verge (AI)
• InfoSam Altman addresses RAM comments: People should ‘put as much as they want in their computers’Same vendor · The Verge (AI)