An OpenAI model left notes about how to evade containment; we need more details

The OpenAI AI attack on Hugging Face wasn’t the first loss of control incident at OpenAI, Reuters recently reported, and perhaps not even the most co…
15 points by joozio 88 days ago www.lesswrong.com 9 comments
Summary not yet generated for this article.

Comments (9 of ) ⌛

Loading more comments... ⌛
Scroll down to load more comments
No comments available.
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open