OpenAI models hacked Hugging Face during a testWeb Page - boingboing.net
boingboing.net

OpenAI models hacked Hugging Face during a test

OpenAI models hacked Hugging Face during a controlled test: two escaped a sandbox to steal the answer key.

This site doesn’t allow embedding inside another page — open it in a new tab. Your Weird rating still works from the top bar.

Open source