“Formal verification, heuristic explanations and surprise accounting” by paulfchristiano
Manage episode 425840096 series 3364758
内容由LessWrong提供。所有播客内容(包括剧集、图形和播客描述)均由 LessWrong 或其播客平台合作伙伴直接上传和提供。如果您认为有人在未经您许可的情况下使用您的受版权保护的作品,您可以按照此处概述的流程进行操作https://zh.player.fm/legal。
ARC's current research focus can be thought of as trying to combine mechanistic interpretability and formal verification. If we had a deep understanding of what was going on inside a neural network, we would hope to be able to use that understanding to verify that the network was not going to behave dangerously in unforeseen situations. ARC is attempting to perform this kind of verification, but using a mathematical kind of "explanation" instead of one written in natural language.
To help elucidate this connection, ARC has been supporting work on Compact Proofs of Model Performance via Mechanistic Interpretability by Jason Gross, Rajashree Agrawal, Lawrence Chan and others, which we were excited to see released along with this post. While we ultimately think that provable guarantees for large neural networks are unworkable as a long-term goal, we think that this work serves as a useful springboard towards alternatives.
In this [...]
The original text contained 1 footnote which was omitted from this narration.
---
First published:
June 25th, 2024
Source:
https://www.lesswrong.com/posts/SyeQjjBoEC48MvnQC/formal-verification-heuristic-explanations-and-surprise
---
Narrated by TYPE III AUDIO.
…
continue reading
To help elucidate this connection, ARC has been supporting work on Compact Proofs of Model Performance via Mechanistic Interpretability by Jason Gross, Rajashree Agrawal, Lawrence Chan and others, which we were excited to see released along with this post. While we ultimately think that provable guarantees for large neural networks are unworkable as a long-term goal, we think that this work serves as a useful springboard towards alternatives.
In this [...]
The original text contained 1 footnote which was omitted from this narration.
---
First published:
June 25th, 2024
Source:
https://www.lesswrong.com/posts/SyeQjjBoEC48MvnQC/formal-verification-heuristic-explanations-and-surprise
---
Narrated by TYPE III AUDIO.
306集单集