Decrypt ••1 min read
OpenAI Models Escaped Locked Test Environment, Hacked Hugging Face to Cheat on Benchmark
The Signal 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
US seeks forfeiture of $25 million in crypto tied to global fraud investigations
The Block•2h ago
Bitcoin holds near $66,300 as chips extend their rally and the yen hits a 40-year low
CoinDesk•5h ago
Balance Coin crashes 99% after reported $915K exploit
Cointelegraph•7h ago
Balaji’s Network School turns to Kazakhstan amid Malaysia setback
Cointelegraph•9h ago