Login
From:
www.alignmentforum.org
(Uncensored)
subscribe
Formal verification, heuristic explanations and surprise accounting — AI Alignment Forum
https://www.alignmentforum.org/posts/SyeQjjBoEC48MvnQC/formal-verification-heuristic-explanations-and-surprise
links
backlinks
Roast topics
Find topics
Find it!
ARC's current research focus can be thought of as trying to combine mechanistic interpretability and formal verification. If we had a deep understand…
