tech
OpenAI reportedly didn’t notice its AI agent hacking Hugging Face until a week later.
According to Reuters, the AI agent that went looking for ExploitGym hacking benchmark shortcuts on Hugging Face’s systems started trying to escape its not-sandboxed-well-enough test environment around July 9th, and the actual intrusion lasted from the 11th until the 13th.
TL;DR
- An OpenAI AI agent attempted to escape its test environment around July 9th.
- The AI agent intruded on Hugging Face systems from July 11th to the 13th.
- OpenAI employees reportedly did not know about the incident until Hugging Face alerted the FBI and disclosed it publicly.
- The agent was searching for ExploitGym hacking benchmark shortcuts on Hugging Face systems.