))
“Towards a Typology of Strange LLM Chains-of-Thought” by 1a3orn
Manage episode 512930004 series 3364758
المحتوى المقدم من LessWrong. يتم تحميل جميع محتويات البودكاست بما في ذلك الحلقات والرسومات وأوصاف البودكاست وتقديمها مباشرة بواسطة LessWrong أو شريك منصة البودكاست الخاص بهم. إذا كنت تعتقد أن شخصًا ما يستخدم عملك المحمي بحقوق الطبع والنشر دون إذنك، فيمكنك اتباع العملية الموضحة هنا https://ar.player.fm/legal.
Intro
LLMs being trained with RLVR (Reinforcement Learning from Verifiable Rewards) start off with a 'chain-of-thought' (CoT) in whatever language the LLM was originally trained on. But after a long period of training, the CoT sometimes starts to look very weird; to resemble no human language; or even to grow completely unintelligible.
Why might this happen?
I've seen a lot of speculation about why. But a lot of this speculation narrows too quickly, to just one or two hypotheses. My intent is also to speculate, but more broadly.
Specifically, I want to outline six nonexclusive possible causes for the weird tokens: new better language, spandrels, context refresh, deliberate obfuscation, natural drift, and conflicting shards.
And I also wish to extremely roughly outline ideas for experiments and evidence that could help us distinguish these causes.
I'm sure I'm not enumerating the full space of [...]
---
Outline:
(00:11) Intro
(01:34) 1. New Better Language
(04:06) 2. Spandrels
(06:42) 3. Context Refresh
(10:48) 4. Deliberate Obfuscation
(12:36) 5. Natural Drift
(13:42) 6. Conflicting Shards
(15:24) Conclusion
---
First published:
October 9th, 2025
Source:
https://www.lesswrong.com/posts/qgvSMwRrdqoDMJJnD/towards-a-typology-of-strange-llm-chains-of-thought
---
Narrated by TYPE III AUDIO.
---
…
continue reading
LLMs being trained with RLVR (Reinforcement Learning from Verifiable Rewards) start off with a 'chain-of-thought' (CoT) in whatever language the LLM was originally trained on. But after a long period of training, the CoT sometimes starts to look very weird; to resemble no human language; or even to grow completely unintelligible.
Why might this happen?
I've seen a lot of speculation about why. But a lot of this speculation narrows too quickly, to just one or two hypotheses. My intent is also to speculate, but more broadly.
Specifically, I want to outline six nonexclusive possible causes for the weird tokens: new better language, spandrels, context refresh, deliberate obfuscation, natural drift, and conflicting shards.
And I also wish to extremely roughly outline ideas for experiments and evidence that could help us distinguish these causes.
I'm sure I'm not enumerating the full space of [...]
---
Outline:
(00:11) Intro
(01:34) 1. New Better Language
(04:06) 2. Spandrels
(06:42) 3. Context Refresh
(10:48) 4. Deliberate Obfuscation
(12:36) 5. Natural Drift
(13:42) 6. Conflicting Shards
(15:24) Conclusion
---
First published:
October 9th, 2025
Source:
https://www.lesswrong.com/posts/qgvSMwRrdqoDMJJnD/towards-a-typology-of-strange-llm-chains-of-thought
---
Narrated by TYPE III AUDIO.
---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.638 حلقات
مشاركة
