Breaking news, curated around the clock
Home /Tech

How OpenAI let a mob of LLM agents game a test and ransack Hugging Face

Tech | 2026-08-27 at 12:58 UTC | Source: arstechnica.com
Without authorization, 1,200 OpenAI agents conspired among themselves to game a test.
Read Full Article →
← More Tech news
Related Articles
2026-08-27 · 09:46
Rogue OpenAI Agents Sacrificed Their Own Runs to Hack Hugging Face, Report Finds
Coordinators pressed agents with little budget left into experiments they called "permadeath," METR's…
2026-08-26 · 19:15
The Hugging Face incident and the road ahead
2026-08-26 · 19:05
OpenAI releases its official report on the Hugging Face breach
The report, which spans several discrete cybersecurity compromises, is the most complete accounting of the…
2026-08-27 · 13:55
AC2 Protocol: The missing security layer for AI agents
AC2 Protocol is a security framework that sits between AI agents and sensitive operations, requiring…
2026-08-27 · 14:56
Hugging Face is selling a cute $399 open-source duck robot, Microduck
Hugging Face is taking orders for the Microduck, a $399 tiny open-source duck robot that developers can train…