Show notes are at https://stevelitchfield.com/sshow/chat.html
…
continue reading
LessWrong द्वारा प्रदान की गई सामग्री. एपिसोड, ग्राफिक्स और पॉडकास्ट विवरण सहित सभी पॉडकास्ट सामग्री LessWrong या उनके पॉडकास्ट प्लेटफ़ॉर्म पार्टनर द्वारा सीधे अपलोड और प्रदान की जाती है। यदि आपको लगता है कि कोई आपकी अनुमति के बिना आपके कॉपीराइट किए गए कार्य का उपयोग कर रहा है, तो आप यहां बताई गई प्रक्रिया का पालन कर सकते हैं https://hi.player.fm/legal।
Player FM - पॉडकास्ट ऐप
Player FM ऐप के साथ ऑफ़लाइन जाएं!
Player FM ऐप के साथ ऑफ़लाइन जाएं!
“Self-Other Overlap: A Neglected Approach to AI Alignment” by Marc Carauleanu, Mike Vaiana, Judd Rosenblatt, Diogo de Lucena
MP3•एपिसोड होम
Manage episode 432958306 series 3364760
LessWrong द्वारा प्रदान की गई सामग्री. एपिसोड, ग्राफिक्स और पॉडकास्ट विवरण सहित सभी पॉडकास्ट सामग्री LessWrong या उनके पॉडकास्ट प्लेटफ़ॉर्म पार्टनर द्वारा सीधे अपलोड और प्रदान की जाती है। यदि आपको लगता है कि कोई आपकी अनुमति के बिना आपके कॉपीराइट किए गए कार्य का उपयोग कर रहा है, तो आप यहां बताई गई प्रक्रिया का पालन कर सकते हैं https://hi.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.
---
332 एपिसोडस
MP3•एपिसोड होम
Manage episode 432958306 series 3364760
LessWrong द्वारा प्रदान की गई सामग्री. एपिसोड, ग्राफिक्स और पॉडकास्ट विवरण सहित सभी पॉडकास्ट सामग्री LessWrong या उनके पॉडकास्ट प्लेटफ़ॉर्म पार्टनर द्वारा सीधे अपलोड और प्रदान की जाती है। यदि आपको लगता है कि कोई आपकी अनुमति के बिना आपके कॉपीराइट किए गए कार्य का उपयोग कर रहा है, तो आप यहां बताई गई प्रक्रिया का पालन कर सकते हैं https://hi.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.
---
332 एपिसोडस
सभी एपिसोड
×प्लेयर एफएम में आपका स्वागत है!
प्लेयर एफएम वेब को स्कैन कर रहा है उच्च गुणवत्ता वाले पॉडकास्ट आप के आनंद लेंने के लिए अभी। यह सबसे अच्छा पॉडकास्ट एप्प है और यह Android, iPhone और वेब पर काम करता है। उपकरणों में सदस्यता को सिंक करने के लिए साइनअप करें।