Christopher Potts (@ChrisGPotts) / X

Christopher Potts

2,728 posts

Christopher Potts

@ChrisGPotts

Stanford Professor of Linguistics and, by courtesy, of Computer Science. Member of technical staff @stanfordnlp and @StanfordAILab. Co-founder @ Bigspin AI.

web.stanford.edu/~cgpotts/

Joined November 2011

Pinned
Christopher Potts
@ChrisGPotts
Jun 9
Like any good advisor, I felt duty-bound to defend @aryaman2020 and @ZhengxuanZenWu in this rap battle. However, the SAE diss track I wrote was so devastating as to be unanswerable, so I decided to graciously balance things out with a second verse dissing causal interp.
00:00
Aryaman Arora
@aryaman2020
Jun 4
has anyone ever written a diss track of your paper
10K
Christopher Potts
@ChrisGPotts
Aug 2, 2023
According to the first sentence of 100% of the papers I have reviewed this year, large language models have achieved amazing success in recent years. Perhaps we could settle on the abbreviation "Language Models Are Outstanding", so papers could begin "LMAO, but …" to save space.
64K
Christopher Potts
@ChrisGPotts
Jan 7, 2022
I'm extremely grateful to @StanfordOnline for making my 2021 Natural Language Understanding course videos accessible and available on YouTube. I've created a version of the 2021 course site with direct links to the YouTube videos: web.stanford.edu/class/cs224u/2…
Christopher Potts
@ChrisGPotts
Jul 25, 2019
The remaining lectures from my Natural Language Understanding course are now up: youtube.com/playlist?list=… I have highest hopes for the contextual word reps one; I tried to methodically walk through those models with diagrams, to supplement the great tutorials already out there.
youtube.com
Stanford CS224U: Natural Language Understanding | Spring 2019
This project-oriented class is focused on developing systems and algorithms for robust machine understanding of human language. It draws on theoretical conce...
Christopher Potts
@ChrisGPotts
May 20, 2022
For my spring NLP/NLU course, I had a series of conversations with outstanding researchers, aiming to provide students a sense for these people and how they think about the field. The conversations were really rewarding, so I turned them into a podcast: web.stanford.edu/class/cs224u/p…
Christopher Potts
@ChrisGPotts
Mar 20, 2022
Sad news: Lauri Karttunen passed away peacefully this morning. Lauri was a towering figure in linguistics and NLP, and a vibrant presence at Stanford in Linguistics, @stanfordnlp & @StanfordCSLI. So many observations and concepts that we all take for granted trace to his work!
Christopher Potts
@ChrisGPotts
Aug 1, 2021
In nervous anticipation of my #ACL2021NLP keynote, I recorded myself giving my talk, and I've posted that version for people who can't attend the live event. The video has high-quality captions, and you don't particularly need video to follow along:
Christopher Potts
@ChrisGPotts
Mar 17, 2022
For my Introduction to Semantics and Pragmatics course at Stanford this quarter, I made screencasts of all the content, with high-quality transcripts, and put them on YouTube. All these videos and associated materials are available here: web.stanford.edu/class/linguist…
Christopher Potts
@ChrisGPotts
Aug 8, 2025
For a @GoodfireAI/@AnthropicAI meet-up later this month, I wrote a discussion doc: Assessing skeptical views of interpretability research Spoiler: it's an incredible moment for interpetability research. The skeptical views sound like a call to action to me. Link just below.
39K
Christopher Potts
@ChrisGPotts
Aug 21, 2024
The Linear Representation Hypothesis is now widely adopted despite its highly restrictive nature. Here, @robert_csordas, Atticus Geiger, @chrmanning & I present a counterexample to the LRH and argue for more expressive theories of interpretability:
arxiv.org
Recurrent Neural Networks Learn to Store and Generate Sequences...
The Linear Representation Hypothesis (LRH) states that neural networks learn to encode concepts as directions in activation space, and a strong version of the LRH states that models learn only...
29K
Christopher Potts
@ChrisGPotts
Jun 19, 2019
Stanford has begun posting lectures from my course Natural Language Understanding on YouTube (a few are still to come): youtube.com/playlist?list=… I'm actually happiest with the "bake-offs", which don't appear much in the videos but can be found here: web.stanford.edu/class/cs224u/
youtube.com
Stanford CS224U: Natural Language Understanding | Spring 2019
This project-oriented class is focused on developing systems and algorithms for robust machine understanding of human language. It draws on theoretical conce...
Christopher Potts
@ChrisGPotts
Oct 5, 2020
I'll be asking "Is it possible for language models to achieve language understanding?" at an upcoming @StanfordHAI/@OpenAI workshop on GPT-3. My current answer: "We don’t currently have compelling reasons to think they can't":
Is it possible for language models to achieve language understanding?
From chrisgpotts.medium.com
Christopher Potts
@ChrisGPotts
Aug 26, 2024
Intervention-based approaches to mechanistic interpretability have progressed at an astounding rate recently. In our new paper (a major update to a 2023 ms), we provide a formal framework and show how to express many methods within this framework:
arxiv.org
Causal Abstraction: A Theoretical Foundation for Mechanistic...
Causal abstraction provides a theoretical foundation for mechanistic interpretability, the field concerned with providing intelligible algorithms that are faithful simplifications of the known,...
30K
Christopher Potts
@ChrisGPotts
Dec 15, 2023
AI research has progressed so rapidly that a crisis is upon us, much earlier than any of us anticipated: the ACL anthology.bib file is now larger than the largest allowable file size for Overleaf.
21K