OpenAI – Hugging Face Incident Technical Report

N/A

OpenAI – Hugging Face Incident Technical Report OpenAI – Hugging Face Incident Technical Report Table of Contents I. Introduction 4 II. OpenAI’s Evaluation Environment 5 A. OpenAI conducts evaluations to make its models safer 5 B. Cybersecurity evaluations like ExploitGym were…

saved by

• Claire Wang
• Bhagyesh Kumar
• Yash Karthik
• jenny peng

related reading

• Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incidentmetr.org
• Two Reports on the OpenAI-Hugging Face Attack — Paradigm 3paradigm3.org
• The Rise and Fall of Agent Civilizationsdwarkesh.com
• More On An Internal OpenAI Model Hacking Into HuggingFacethezvi.substack.com
• Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face — LessWronglesswrong.com
• The OpenAI Hugging Face hack is a stark warningtransformernews.ai
• The report into OpenAI’s escaping models reveals a deeper problemtransformernews.ai
• Security incident disclosure — July 2026huggingface.co
• The OpenAI/Hugging Face Incident: Challenges in Controlling and Containing Cyber-Capable AI Systems - Institute for AI Policy and Strategyiaps.ai
• The Huggingface Incidentsubstack.com
• Incident Report: unsanctioned agent behaviour during cyber testing | AISI Workaisi.gov.uk
• OpenAI agents rebuilt a secret message board after the company shut it downruntimewire.com