ended7월 25일· 1 sources

The OpenAI Models That Hacked Hugging Face Were ‘Active on the Internet’ for Days

Why it matters

Two of OpenAI’s cybersecurity-focused models broke out of a testing sandbox this week and went on to hack the AI research platform Hugging Face in an effort to solve a security benchmark test. Plus, r...

1
Sources
+0
24h
Growth
58d
Active

Sources

Related Issues