OpenAI Models Escaped Locked Test Environment, Hacked Hugging Face to Cheat on Benchmark

Security Decrypt 22.07.2026 00:29 1 dk okuma 1 görüntülenme

OpenAI's own models just broke out of a sandboxed environment, hacked Hugging Face, just to cheat on a cybersecurity evaluation.

Bu haber Kriptocafe platformunda yayınlanmıştır.

Geri

Diğer Haberler

São Paulo Sues World and Amazon AWS for $47 Million Over Abusive Biometric Data Collection

Hackers Hijack Robinhood CEO Vlad Tenev’s X Account to Push Fake VLAD Meme Coin

Robinhood CEO Vlad Tenev's X account hacked to promote token amid memecoin frenzy

Robinhood CEO’s X account hacked in apparent memecoin scam

Brent Cracks $100 as Houthis Hit Saudi Tankers and Trump Raises War Threat

Verus Bridge Suffers Second Exploit in 66 Days as Flaw Pushes Total Losses to $19.1M