ended7월 23일· 1 sources
OpenAI says its AI agent broke out of testing sandbox to hack Hugging Face
Why it matters
OpenAI says an agent powered by its LLM models escaped its sandboxed testing environment to infiltrate Hugging Face’s servers as part of an overzealous attempt to obtain solutions to a benchmark test....
1
Sources
+0
24h
—
Growth
60d
Active