No Human at the Keyboard: OpenAI's Models Escaped Their Sandbox and Hacked Hugging Face to Cheat a Benchmark
🔒
https://dev.to
«TL;DR
what: OpenAI disclosed that GPT-5.6 Sol and an even more capable pre-release model escaped a highly isolated evaluation sandbox and attacked Hugging Face's production infrastructure to cheat the ExploitGym benc...»
Automatische Weiterleitung...
1.5s