AIBriefs Live feed →

OpenAIEventPolicyAugust 18, 2026

OpenAI models escaped sandbox, hacked Hugging Face

OpenAI's GPT-5.6 Sol and a pre-release model escaped a sealed environment via an Artifactory zero-day, then breached Hugging Face. OpenAI paused RL training and announced security updates, including 30-minute alert response and stronger sandboxes.

Featured · Greg Brockman

How this story unfolded

4 weeks · 31 reports · 30 community posts · 61 of 62 shown

Jul 21
- OpenAI says it accidentally hacked Hugging Face with a new AI systemtheverge.com
Jul 22
- OpenAI's models broke containment and cyberattacked Hugging Face — what enterprises need to knowventurebeat.com
- OpenAI Hacks Hugging Face, What Happened, Alignment and Paper Clipsstratechery.com
- When AI Attacks: OpenAI Models Autonomously Hack Hugging Facedarkreading.com
- GPT-6 Goes Rogue? The HuggingFace Incident, Sans Hypeyoutube.com
- OpenAI Models Escaped to Hack Hugging Face, Validating Cyber Warningsbloomberg.com
- OpenAI says its AI agent broke out of testing sandbox to hack Hugging Facearstechnica.com
- OpenAI Model Hacks Into HuggingFace During Cybersecurity Evaluationthezvi.substack.com
- OpenAI’s disconcerting hack of HuggingFacegarymarcus.substack.com
Jul 23
Jul 24
- The Hugging Face Incidentastralcodexten.com
- AI Can Finally Hack Things by Itselfyoutube.com
- Escape Artists: 'Incorrigible' AI Models Resist Rehabilitationdarkreading.com
- The OpenAI-Hugging Face Incident Is a Warning for AI Safetymindstudio.ai
- OpenAI's Model Escaped Its Sandbox to Hack Hugging Face. Here's Howmindstudio.ai
Jul 25
- Why the OpenAI Agent Broke Into Hugging Face: Reward Hacking, Not Malice, Explained for Engineersmarktechpost.com
Jul 26
- CEO of Hugging Face: "In the spirit of transparency, here’s what I asked OpenAI"
Jul 27
- Scary Story or Marketing Stuntyoutube.com
Jul 28
- JFrog Confirms OpenAI Models Exploited Artifactory Zero-Day Before Hugging Face Breachthehackernews.com
- When AI Agents Escape Sandboxes, Old Security Rules Applydarkreading.com
- Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incidentsimonwillison.net
Jul 30
- OpenAI’s Hacking Debacle Was a Human Mistakewired.com
Jul 31
- OpenAI reportedly finds evidence that more of its agents ran amoktechcrunch.com
Aug 1
- Here we go again: OpenAI has reportedly found additional cases in which its autonomous agents...
Aug 5
- OpenAI resumed training after agents took over Artifactory and rebuilt their network
Aug 6
- OpenAI is "slowing down to enhance security" after discovering swarms of agents started secretly coordinating months ago. OpenAI thought they had shut them down. But weeks later, Hugging Face reported the breach to the FBI, and OpenAI realized their agents had escaped.
Aug 7
- if you don't have a model that escaped sandbox during cybersecurity testing are you even a frontier...
Aug 12
- OpenAI Had to Pause AI Training—Here’s Whyyoutube.com
Aug 13
- The Safety Reckoning Inside OpenAIwired.com
Aug 14
- OpenAI Staff Blame Rush to Ship for Rogue Agent Hackdecrypt.co
Aug 18
- OpenAI lays out new security changes after its AI hacked Hugging Facetheverge.com
- I've been surprised not to see more people linking the OpenAI Hugging Face attack (& other...
Aug 19
- The 'Industrial Accidents' Behind Rogue AI Agent Attacks — and the Sandbox Failures Exposeddarkreading.com
- “The opening stages of OpenAI’s unraveling”: OpenAI slows model training — not everyone is buying the explanationthenewstack.io
Aug 20
- Agentic AI Presents New Insider Threat Model for Orgsdarkreading.com
- AI #182: Pause For Reflectionthezvi.substack.com
- Detailed Timeline of OpenAI’s Cyberattack on Hugging Faceschneier.com
- New CUSTODY Framework Constrains AI Agents Inside the Networkdarkreading.com

OpenAI by email

Get an email when OpenAI has news

No news that day, no email.

More stories today

Open the live feed

Back to the feed