
Sign up to save your podcasts
Or


Summary
When discussing the possibility that LLMs will cease to reason in transparent natural language with other AI safety researchers, we have sometimes noticed that we talk past each other: e.g., when discussing ‘neuralese reasoning’, some people have indefinitely long chains of recurrent activations in mind, while others think of an alien language in token-space. This post will propose terminology for distinguishing different types of hidden reasoning to create a shared language for such conversations.
In short, our taxonomy categorizes types of hidden reasoning as follows:
---
Outline:
(00:10) Summary
(02:47) Taxonomy
(04:26) Recurrent neuralese reasoning
(04:55) Hidden parallelized reasoning
(07:51) Steganography
(10:21) Linguistic drift
(11:38) Dazzling
(12:20) Examples in the Wild
(12:24) Neuralese
(13:05) Hidden parallelized reasoning
(15:20) Steganography
(15:23) Semantic steganography
(17:15) Lexical steganography through steganographically embedded ciphers
(18:21) Lexical steganography through internal token layering
(19:52) Linguistic drift
(21:26) Dazzling
(21:29) Post-hoc justifications
(22:35) Manipulation
(23:04) Some additional categories
(25:09) Canary string
(25:25) Acknowledgements
The original text contained 4 footnotes which were omitted from this narration.
---
First published:
Source:
---
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.
By LessWrongSummary
When discussing the possibility that LLMs will cease to reason in transparent natural language with other AI safety researchers, we have sometimes noticed that we talk past each other: e.g., when discussing ‘neuralese reasoning’, some people have indefinitely long chains of recurrent activations in mind, while others think of an alien language in token-space. This post will propose terminology for distinguishing different types of hidden reasoning to create a shared language for such conversations.
In short, our taxonomy categorizes types of hidden reasoning as follows:
---
Outline:
(00:10) Summary
(02:47) Taxonomy
(04:26) Recurrent neuralese reasoning
(04:55) Hidden parallelized reasoning
(07:51) Steganography
(10:21) Linguistic drift
(11:38) Dazzling
(12:20) Examples in the Wild
(12:24) Neuralese
(13:05) Hidden parallelized reasoning
(15:20) Steganography
(15:23) Semantic steganography
(17:15) Lexical steganography through steganographically embedded ciphers
(18:21) Lexical steganography through internal token layering
(19:52) Linguistic drift
(21:26) Dazzling
(21:29) Post-hoc justifications
(22:35) Manipulation
(23:04) Some additional categories
(25:09) Canary string
(25:25) Acknowledgements
The original text contained 4 footnotes which were omitted from this narration.
---
First published:
Source:
---
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.

26,387 Listeners

2,423 Listeners

8,491 Listeners

4,149 Listeners

92 Listeners

1,584 Listeners

9,833 Listeners

89 Listeners

489 Listeners

5,470 Listeners

16,072 Listeners

534 Listeners

133 Listeners

96 Listeners

508 Listeners