In QS’s newly released World University Rankings by Subject 2025: Library & Information Management, the University of Texas at Austin School of Information ranks #5 globally and #3 in the United States! Read more: ischool.utexas.edu/news/ut-ranks-…

Wonderful opportunity if you are interested in responsible AI research

We're #hiring a Career Coach! This position will provide one-on-one career coaching, targeted career programming/resources, and career education to School of Information undergraduate and graduate students. Apply today or share this post with your network! ischool.utexas.edu/about/jobs

What if you could understand and control an LLM by studying its *smaller* sibling? Our new paper proposes the Linear Representation Transferability Hypothesis: internal representations of different-sized models can be translated via a simple linear (affine) map.

This has huge practical implications! It opens the door to using small, efficient models as sandboxes to probe, understand, and even steer their much larger counterparts. Paper: arxiv.org/abs/2506.00653 Joint work with femi, Anubrata Das 🦋 @ NAACL 2025, Fanzhi Zeng, Fangcong Yin

yuwen lu HCI methodology is going to be a central focus of AI as the field starts to recognize that most tasks involve an unavoidable human element and measuring stuff with humans is hard. It’s starting with uplift studies and will continue.

maybe I will live tweet the actionable interp workshop panel

Writing is thinking | Nature Reviews Bioengineering share.google/DVwJKHxWu8fOTy…

Btw as an aside, we didn’t announce on Friday because we respected the IMO Board's original request that all AI labs share their results only after the official results had been verified by independent experts & the students had rightly received the acclamation they deserved

New method to crack hard reasoning problems with LLM! No expert traces. No test-time hacks. Just: Self-explanation + RL-style training Result? Accuracy on MATH level-5 jumped from 2% → 23%

🧵 Academic job market season is almost here! There's so much rarely discussed—nutrition, mental and physical health, uncertainty, and more. I'm sharing my statements, essential blogs, and personal lessons here, with more to come in the upcoming weeks! ⬇️ (1/N)

Producing reasoning texts boosts the capabilities of AI models, but do we humans correctly understand these texts? Our latest research suggests that we do not. This highlights a new angle on the "Are they transparent?" debate: they might be, but we misinterpret them. 🧵

Many people are confused in this way about education. "If an LLM can write an essay, why are you still assigning essays, the whole ed system is broken lol" No— you don't write an essay to produce an essay. You write an essay to level up the brain that produced the essay. /end

Youtube playlist for AI safety course is on youtube.com/playlist?list=…

Teaching a new course Stanford University this quarter on explainable AI, motivated by neuroscience. I have curated a paper list 4 pages long (link in comment). What are your favorite papers on explainable AI/mechanistic interpretability that I am missing? Please comment or DM. thanks!

The compling group at UT Austin (sites.utexas.edu/compling/) is looking for PhD students! Come join me, Kyle Mahowald, and Jessy Li as we tackle interesting research questions at the intersection of ling, cogsci, and ai! Some topics I am particularly interested in:

All of us (Kyle Mahowald, Kanishka Misra 🌊 and me) are looking for PhD students this cycle! If computational linguistics/NLP is your passion, join us at UT Austin! For my areas see jessyli.com

It is PhD application season again 🍂 For those looking to do a PhD in AI, these are some useful resources 🤖: 1. Examples of statements of purpose (SOPs) for computer science PhD programs: cs-sop.org [1/4]

Privacy in LLMs is not just Memorization! We reviewed 1322 papers (2016–25) across ML, NLP & SEC: 92% fixate on memorization/chat leaks. We map 5 urgent problems + a roadmap, to prevent surveillance, inference, aggregation and other negative outcomes.

Many this morning came early to attend Nicholas Carlini's keynote at #COLM2025. He spoke up to bring awareness on a range of problems with LLM use, summarized by the question: are they worth it? Here I report his main points and why they deserve attention. 🧵