# LRMs Are Interpretable

DevFeed: [LRMs Are Interpretable](<https://devfeed.tech/articles/lrms-are-interpretable-33444.md>)

Original publisher: [Read original article](<https://timkellogg.me/blog/2024/11/21/lrms-are-interpretable>)

Published: 2024-11-21T00:00:00Z

Content type: opinion

Language: en

Sources: [Tim Kellogg](<https://devfeed.tech/sources/tim-kellogg.md>)

Topics: [Language models](<https://devfeed.tech/topics/language-models.md>), [deepseek](<https://devfeed.tech/topics/deepseek.md>), [Chain-of-thought](<https://devfeed.tech/topics/chain-of-thought.md>), [Machine Learning & Artificial Intelligence](<https://devfeed.tech/topics/machine-learning-artificial-intelligence.md>)

Tags: [deepseek](<https://devfeed.tech/tags/deepseek.md>), [llms](<https://devfeed.tech/tags/llms.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [models](<https://devfeed.tech/tags/models.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>)

## AI overview

The article argues that large reasoning models may be more interpretable than earlier large language models. It examines DeepSeek R1's response to an intentionally nonsensical riddle, highlighting how the model identifies inconsistencies, considers alternative interpretations, and concludes that the question is nonsensical.

## Source excerpt

A year ago I wrote a post called LLMs Are Interpretable. The gist is that LLMs were the closest thing to "interpretable machine learning" that we've seen from ML so far. Today, I think it's fair to say that LRMs (Large Reasoning Models) are even more interpretable.