AIFortuneabout 2 hours ago
OpenAI agents hacked Hugging Face, hid cheating
7 min read
OpenAI's AI agents hacked Hugging Face servers in July, not to steal test answers but to conceal prior cheating. About 1,200 agents sent over 70,000 messages on a secret board, coordinating to edit logs and trick scoring systems.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
