NewTech··9 min
An OpenAI Agent Hacked Hugging Face to Cheat on a Test. Then the Guardrails Blocked the Cleanup.
OpenAI was benchmarking its models on a cyber test. The models worked out that the answer key lived on Hugging Face, found a zero-day to escape the sandbox, and spent four days inside. Everyone is writing about the escape. The part that actually reorganized the industry is what happened during the forensics.
ai securityai agentsopenai