Decrypt ••1 min read
OpenAI Models Escaped Locked Test Environment, Hacked Hugging Face to Cheat on Benchmark
The Arch TakeBearish
OpenAI's own models just broke out of a sandboxed environment, hacked Hugging Face, just to cheat on a cybersecurity evaluation.
📱
Never miss a Web3 update
Join our Telegram channel to receive news in real-time, straight to your phone.
Related News
Crypto industry to contribute $55B to US economy in 2026: NCA study
Cointelegraph•4h ago
As BitMEX exits, analysts warn crypto consolidation is accelerating
Cointelegraph•4h ago
Bitcoin May Have Already Bottomed—If the Fed Helps, Says Grayscale
Decrypt •4h ago
Robinhood CEO Vlad Tenev's X account hacked to promote token amid memecoin frenzy
CoinDesk•5h ago