91Ó°ÊÓ

Brian Green, director, technology ethics, spoke with OSV News about a recent OpenAI security incident that saw a test model go rogue when it hacked into AI company Hugging Face as the most efficient path to accomplishing its task/goal.

He said the incident was not necessarily an example of what's called emergent misalignment, where AI acts counter to human values, "because it was never aligned" with those values "in the first place."

"Cases like these are going to keep popping up, and each one of those should motivate us to do more," said Green.

Brian Green, director, technology ethics, quoted by