Chenhao Tan
@ChenhaoTan
Followers
4K
Following
7K
Media
131
Statuses
2K
Professor @UChicagoCS @UChicago. Directing @ChicagoHAI, also part of @UChicagoCI. Email for Postdoc/PhD opportunities.
Chicago, IL
Joined June 2012
AI can accelerate scientific discovery, but only if we get the scientist–AI interaction right. The dream of “autonomous AI scientists” is tempting: machines that generate hypotheses, run experiments, and write papers. But science isn’t just an automation problem — it’s also a
12
56
262
Excited about this talk on Asta by @_DougDowney !
0
0
8
❓ Does an LLM know thyself? 🪞 Humans pass the mirror test at ~18 months 👶 But what about LLMs? Can they recognize their own writing — or even admit authorship at all? In our new paper, we put 10 state-of-the-art models to the test. Read on 👇 1/n 🧵
2
13
24
Excited to release BoltzGen which brings SOTA folding performance to binder design! The best part of this project has been collaborating with many leading biologists who tested BoltzGen at an unprecedented scale, showing success on many novel targets and pushing its limits! 🧵..
14
209
735
STOC 2026 is offering experimental pre-submission feedback using an AI tool optimized for checking mathematical rigor. Results won't go to PC or be used for training purposes. Opt-in via the submission server by November 1. Details:
0
6
26
I used ChatGPT to solve an open problem in convex optimization. *Part I* (1/N)
78
343
2K
We're over-indexing on the negatives of AI companions. While the risks are real, the panic-driven narrative ignores the massive, stigmatized crisis of loneliness they're trying to solve. I wrote a short post on the positive use cases we shouldn't ignore https://t.co/ZvkxBkJswy
0
2
6
Remembering Chen Ning Yang, PhD'48, the Nobel Prize-winning physicist who redefined our understanding the nature of particles. Yang wrote his Ph.D. dissertation on the concepts of symmetry and natural phenomenon—themes of his field-defining research.
news.uchicago.edu
UChicago alum made groundbreaking discoveries on the nature of particles
2
9
31
Great advice for human evaluators of LLM writing or editing!
While reviewing for #CHI2026, I noticed four new writing issues, likely due to increased use of LLMs. I describe them here - and how to fix them:
2
0
9
arxiv.org
Language models are increasingly capable, yet still fail at a seemingly simple task of multi-digit multiplication. In this work, we study why, by reverse-engineering a model that successfully...
AI can write complex code but fails at 4-digit multiplication. 🤔 New research by @Elenal3ai & @ChenhaoTan reveals why billions of parameters can't solve grade-school math—and what it takes to fix it. It's about how AI learns, not how much it learns.
0
1
6
starting now!!!
This week we are excited to have @yuqirose sharing her work on grounding foundation models for physical sciences!
0
1
2
We just launched Mojo🔥 GPU Puzzles Edition 1, a hands-on guide that teaches GPU programming through 34 progressive challenges, not lectures. Learn by doing, from your first GPU threads to tensor cores. Works on NVIDIA, AMD, and Apple GPUs. https://t.co/nXy5cDSJCU
puzzles.modular.com
Learn GPU Programming in Mojo🔥 Through Interactive Puzzles
12
122
864
There are still open desks in our new Human & Machine Intelligence lab at Princeton. Express your interest in joining us: https://t.co/4wbiO2yWr9
7
53
323
🎉Honored to be named a 2025 Google PhD Fellow!! Grateful to my advisor & collaborators. I’ve been fortunate to explore the frontier of HCI—interfacing w/ the brain & nerves to empower users. I hope to keep advancing this as a faculty. I'm on job market! https://t.co/SaVPFynYSx
22
38
427
🙏 great to see people summarizing your work better than yourself!
Very cool idea! Collective idea generation / selection to oversee AI research agents.
0
0
2
I am also working on curating a list of resources towards this goal: https://t.co/7PecZYd5a6. Please add your favorite tools in this space.
github.com
Contribute to ChicagoHAI/future-of-science-roadmap development by creating an account on GitHub.
making a video testing every AI scientist/AI research agent platform: @FutureHouseSF
@the_scienceOS
@Scite
@perplexity_ai
@elicitorg any others i'm missing?
0
0
10
Check this quick demo by @HaokunLiu5280 :
AI can accelerate scientific discovery, but only if we get the scientist–AI interaction right. The dream of “autonomous AI scientists” is tempting: machines that generate hypotheses, run experiments, and write papers. But science isn’t just an automation problem — it’s also a
0
0
1
Thank @universeinanegg @ianfoster @profjamesevans @haopeng_uiuc @amt_shrma @Ted_Underwood for their helpful feedback!
1
0
2
It’s here! #Agents4Science recording is now on YouTube! 🏆 3 Best Paper talks ⚡️ 11 Spotlights 🧠 Panel on the future of AI agent-driven science 📚 Lessons + surprises from this first-of-its kind conf Full analysis of submissions + reviews coming soon! https://t.co/k4ksIWRaZy
3
31
131