“Towards a Typology of Strange LLM Chains-of-Thought” by 1a3orn

LessWrong (Curated & Popular)

Content provided by LessWrong. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by LessWrong or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://podcastplayer.com/legal.

16d ago 17:34

MP3•Episode home

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.
---

Images from the article:

Table comparing unusual word frequencies between OpenAI o3 and GPQA baseline.

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

646 episodes

#Tech #Society #Philosophy #LessWrong #LessWrong Curated