))
“Self-Other Overlap: A Neglected Approach to AI Alignment” by Marc Carauleanu, Mike Vaiana, Judd Rosenblatt, Diogo de Lucena
Manage episode 432959397 series 3364758
İçerik LessWrong tarafından sağlanmıştır. Bölümler, grafikler ve podcast açıklamaları dahil tüm podcast içeriği doğrudan LessWrong veya podcast platform ortağı tarafından yüklenir ve sağlanır. Birinin telif hakkıyla korunan çalışmanızı izniniz olmadan kullandığını düşünüyorsanız burada https://tr.player.fm/legal özetlenen süreci takip edebilirsiniz.
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.
---
363 bölüm
Paylaş
