chenhaotan.bsky.social
@chenhaotan.bsky.social
Associate professor at the University of Chicago. Working on human-centered AI, NLP, CSS. https://chenhaot.com, https://substack.com/@cichicago
Pinned
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 automation.

cichicago.substack.com/p/the-mirage...
🧵
The Mirage of Autonomous AI Scientists
Science as AI’s killer application cannot succeed without scientist-AI interaction: Introducing Hypogenic.ai.
cichicago.substack.com
Reposted
🚀Week 2 Results: Research AI Agents Making Progress

Huge thanks to everyone who participated!

Full blog:
hypogenic.ai/blog/weekly-...

More info in thread👇
Hypogenic AI - Shaping the Future of Science
Reimagining science by augmenting scientist-AI collaboration.
hypogenic.ai
November 25, 2025 at 8:07 PM
Reposted
I'm recruiting my first group of students at TTIC! If you're interested, please apply by December 9th and mention my name in your application
Pursue a fully-funded and personalized PhD in #computerscience with world-class faculty as mentors, a 4:1 student-to-faculty ratio, and in the vibrant city of Chicago. Learn more and apply by Dec. 9 (NO FEE): buff.ly/Qw8njWB
November 24, 2025 at 5:58 PM
Come chat with us at the poster! We will bring some unicorn ducks too!
Will be at #NeurIPS2025 presenting “Concept Incongruence”!

🦄🦆 Curious about a unicorn duck? Stop by, get one, and chat with us!

We made a new demo for detecting hidden conflicts in system prompts to spot “concept incongruence” for safer prompts.

🔗: github.com/ChicagoHAI/d...

🗓️ Dec 3 11AM - 2PM
November 24, 2025 at 7:25 PM
Academic peer review has mostly treated paper as the single source of truth, even when the accompanying code is available. We can change this with research agents, and there is a lot of exciting work going forward! If interested, reach out to Xiaoyan or me!
Research agents are getting smarter. They can write convincing PhD-level reports 🧑‍🔬

But has anyone checked if the way they find their results makes any sense?

Our framework, MechEvalAgents, verifies the science, not just the story 🤖

1/n🧵
November 20, 2025 at 11:12 PM
Reposted
Calling NYC parents -- after years of requests we finally offer a summer high school program on campus.
Cornell Tech is launching a new Summer Innovation Intensive for high schoolers! Explore AI, ethical coding, data science & product design on our Roosevelt Island campus this July.

Join us at our Open Houses on Dec 7 & 11.
https://tech.cornell.edu/programs/summer-innovation-intensives/
November 14, 2025 at 9:38 PM
Reposted
We're launching a weekly competition where the community decides which research ideas get implemented. Every week, we'll take the top 3 ideas from IdeaHub, run experiments with AI agents, and share everything: code, successes, and failures.

It's completely free and we'll try out ideas for you!
November 10, 2025 at 9:32 PM
Reposted
Econ, artificial intelligence and machine learning …
#EconConf #econsky
marketdesigner.blogspot.com/2025/11/econ...
Economics and CS (AI+ML) in Ithaca in June: call for papers
marketdesigner.blogspot.com
November 9, 2025 at 2:08 PM
Reposted
If you're a student in need of a personal website (and if you're doing research, yes, you need a website!), I keep a list of nice examples here, most of which are reusable: www.are.na/maria-antoni...

For example, I just spotted this beautiful website by Catherine Yeh: github.com/catherinesye...
November 3, 2025 at 8:11 PM
Recruiting PhDs & postdocs for:

🤖 agents "taking over" science (hypogenic.ai and 📌)
🧪 Real scientists ➡️AI (e.g., materials, chem, physics)
📜 Theory + incentives for H-AI collab & credit (e.g., formalizing tacit knowledge)

new adventures for me, 🔄 if you can! 🙌

chenhaot.com/recruiting.h...
Chenhao Tan's Homepage - recruiting
Chenhao Tan's Homepage
chenhaot.com
November 3, 2025 at 8:06 PM
Due to a speaker conflict, we will have the online seminar on **Thursday** at 12pm ET/11am CT/9am PT. Come to learn about AI & Scientific Discovery in material science!

ai-scientific-discovery.github.io
November 3, 2025 at 4:50 PM
Reposted
Identifying human morals and values in language is crucial for analysing lots of human- and AI-generated text.

We introduce "MoVa: Towards Generalizable Classification of Human Morals and Values" - to be presented at @emnlpmeeting.bsky.social oral session next Thu #CompSocialScience #LLMs
🧵 (1/n)
October 30, 2025 at 12:20 AM
GPT and Claude appears at high status in this model recognition task.
🕸️ Here’s a network showing how much different models predict each other as the author of some text!
October 28, 2025 at 2:00 AM
October 27, 2025 at 6:02 PM
Reposted
❓ 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 🧵
October 27, 2025 at 5:36 PM
Yes, more companies should move to Chicago!
Chicago is a city, a far better (and bigger) one than Seattle? It's not a purge if you move your company somewhere you can afford? I'm not suggesting living in a woods. There are lots of communities with great hipster restaurants & entertainment even in the rustbelt, you just have to look a little.
October 26, 2025 at 5:33 PM
Reposted
AI can write complex code but fails at 4-digit multiplication. 🤔 New research by @elenal3ai.bsky.social & @chenhaotan.bsky.social 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.
Read more: bit.ly/3Jp59RT
October 24, 2025 at 5:56 PM
Reposted
Every clause in this (on AI science) !!! 👇👇
It’s also a resource allocation problem: deciding what matters, which hypotheses to test, and which results to trust.

Automation can produce knowledge, but meaning comes from human judgment.
October 23, 2025 at 9:02 PM
October 23, 2025 at 7:13 PM
Reposted
That’s why we’re introducing Hypogenic.ai, a platform designed for idea selection and evaluation.
💡 IdeaHub: collective rating and discussion of research ideas.
🧠 Ideation Assistant: AI-driven research ideation.
Hypogenic AI - Shaping the Future of Science
Reimagining science by augmenting scientist-AI collaboration.
Hypogenic.ai
October 23, 2025 at 6:56 PM
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 automation.

cichicago.substack.com/p/the-mirage...
🧵
The Mirage of Autonomous AI Scientists
Science as AI’s killer application cannot succeed without scientist-AI interaction: Introducing Hypogenic.ai.
cichicago.substack.com
October 23, 2025 at 6:55 PM
This week we will have Rose Yu from UCSD sharing her work on grounding foundation models for physical sciences!

ai-scientific-discovery.github.io
October 20, 2025 at 10:10 PM
Reposted
We’re excited to release the Call for Papers for #FAccT2026 which will be held in Montreal, Canada in June 2026! Abstracts are due on January 8th, papers due on January 13th.

Call for Papers: facctconference.org/2026/cfp

Important info in thread →
ACM FAccT - 2026 CFP
facctconference.org
October 17, 2025 at 1:27 PM
Happening in two hours!
This week we will have two speakers at the AI & Scientific Discovery online seminar: Yihang Wang and Jiachen Yao!

ai-scientific-discovery.github.io
October 17, 2025 at 2:00 PM
This week we will have two speakers at the AI & Scientific Discovery online seminar: Yihang Wang and Jiachen Yao!

ai-scientific-discovery.github.io
October 14, 2025 at 5:15 PM