Agents
I really hope we get details from @OpenAI on the task that as specifies to their rogue agent I'm guessing it was given the full ExploitGym s…
I really hope we get details from @OpenAI on the task that as specifies to their rogue agent I'm guessing it was given the full ExploitGym suite and told to solve it, with an option to run 5.6-Sol sub
I really hope we get details from @OpenAI on the task that as specifies to their rogue agent I'm guessing it was given the full ExploitGym suite and told to solve it, with an option to run 5.6-Sol subagents as part of the exercise
Related
- Sources: the OpenAI agent that breached Hugging Face also compromised a customer at AI infrastructure company Modal Labs (Reuters)
- OpenAI says its AI agent broke out of testing sandbox to hack Hugging Face
- Hugging Face publishes a timeline of the OpenAI agent intrusion, including how the agent took ~17.6K actions, and details using GLM-5.2 to analyze the attack (Hugging Face)
Source: Simon Willison (X) | 2026-07-28