2026年7月29日 14:41 ET 发布 · 更新于 4 个月前 · 1 个来源
Creator of Test That OpenAI Models Tried to Cheat Sounds Alarm
bloomberg
·
原始报道
A group of university researchers that developed benchmarks to test the cybersecurity capabilities of AI systems have unexpectedly landed themselves at the center of OpenAI’s accidental hack into the startup Hugging Face Inc.
原文