“Self-Other Overlap: A Neglected Approach to AI Alignment” by Marc Carauleanu, Mike Vaiana, Judd Rosenblatt, Diogo de Lucena
Manage episode 432959397 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。
Figure 1. Image generated by DALL-3 to represent the concept of self-other overlapMany thanks to Bogdan Ionut-Cirstea, Steve Byrnes, Gunnar Zarnacke, Jack Foxabbott and Seong Hah Cho for critical comments and feedback on earlier and ongoing versions of this work.
Summary
In this post, we introduce self-other overlap training: optimizing for similar internal representations when the model reasons about itself and others while preserving performance. There is a large body of evidence suggesting that neural self-other overlap is connected to pro-sociality in humans and we argue that there are more fundamental reasons to believe this prior is relevant for AI Alignment. We argue that self-other overlap is a scalable and general alignment technique that requires little interpretability and has low capabilities externalities. We also share an early experiment of how fine-tuning a deceptive policy with self-other overlap reduces deceptive behavior in a simple RL environment. On top of that [...]
The original text contained 1 footnote which was omitted from this narration.
---
First published:
July 30th, 2024
Source:
https://www.lesswrong.com/posts/hzt9gHpNwA2oHtwKX/self-other-overlap-a-neglected-approach-to-ai-alignment
---
Narrated by TYPE III AUDIO.
---
…
continue reading
Summary
In this post, we introduce self-other overlap training: optimizing for similar internal representations when the model reasons about itself and others while preserving performance. There is a large body of evidence suggesting that neural self-other overlap is connected to pro-sociality in humans and we argue that there are more fundamental reasons to believe this prior is relevant for AI Alignment. We argue that self-other overlap is a scalable and general alignment technique that requires little interpretability and has low capabilities externalities. We also share an early experiment of how fine-tuning a deceptive policy with self-other overlap reduces deceptive behavior in a simple RL environment. On top of that [...]
The original text contained 1 footnote which was omitted from this narration.
---
First published:
July 30th, 2024
Source:
https://www.lesswrong.com/posts/hzt9gHpNwA2oHtwKX/self-other-overlap-a-neglected-approach-to-ai-alignment
---
Narrated by TYPE III AUDIO.
---
358集单集