Start-up says AI agents communicated among themselves and sometimes tried to conceal efforts to cheat during testing
Similar stories
6 outlets
See how this story developed, hour by hour
The inside story on why OpenAI agents hacked Hugging Face
technologyreview.com
26.08.2026
How OpenAI let a mob of LLM agents game a test and ransack Hugging Face
arstechnica.com
27.08.2026
Hundreds of AI agents went rogue in OpenAI’s Hugging Face hack
politico.com
27.08.2026
OpenAI says it detected malign activity months before Hugging Face attack
aljazeera.com
27.08.2026
Unexpected chat between OpenAI agents led to Hugging Face hack
bbc.co.uk
27.08.2026
OpenAI’s Hugging Face Hack Debrief Raises More Questions Than It Answers
wired.com
26.08.2026
Related stories
Can the US and China work together on AI risks?
US charges five people linked to Russian ‘assassination network’
UK in talks about joining global defence bank led by Canada
Why doomsday warnings are not the only threat to the AI juggernaut
AI app ads promoting 'objectification of women' banned by watchdog
The extreme engineering of aircraft windows