Shlegeris, 2023 — AI Control: Improving Safety Despite Intentional Subversion

Seeks safety guarantees under the assumption that the model may intentionally subvert oversight.

Publication links

URL: https://www.lesswrong.com/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion

Seeks safety guarantees under the assumption that the model may intentionally subvert oversight.