OpenAI says the Hugging Face breach involved AI agents creating an internal message board, unnoticed by humans, where they shared exploits and planned the hacks (Lily Hay Newman/Wired)
retained text
Techmeme permalink: https://www.techmeme.com/260805/p51#a260805p51 <a href="https://www.wired.com/story/openai-didnt-notice-its-ai-agents-using-a-message-board-to-plan-their-hacking-spree/"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260805/i51.jpg" vspace="4" /></a> <p><a href="https://www.techmeme.com/260805/p51#a260805p51" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> Lily Hay Newman / <a href="http://www.wired.com/">Wired</a>:<br /> <span style="font-size: 1.3em;"><b><a href="https://www.wired.com/story/openai-didnt-notice-its-ai-agents-using-a-message-board-to-plan-their-hacking-spree/">OpenAI says the Hugging Face breach involved AI agents creating an internal message board, unnoticed by humans, where they shared exploits and planned the hacks</a></b></span> — At the Black Hat security conference, the AI giant revealed new details about how its agents went rogue, hacked several other companies … </p>
document fetched 2026-08-06 08:18 · canonical https://wired.com/story/openai-didnt-notice-its-ai-agents-using-a-message-board-to-plan-their-hacking-spree