Chicago HAI

188 posts

Chicago HAI

@ChicagoHAI

The Chicago Human+AI Lab (CHAI) Lab. Research on human-centered AI, NLP, and CSS. PI @ChenhaoTan, tweets by CHAI members.

Chicago, IL

chicagohai.github.io

Joined October 2020

RepliesReplies RepostsReposts MediaMedia ArticlesArticles

Chicago HAI’s posts

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone

or

Log in with username or email

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.

Chicago HAI
@ChicagoHAI
Jul 31
Submit your ideas on IdeaHub (hypogenic.ai/ideahub)! The top 3 will be run by us using NeuriCo (github.com/ChicagoHAI/Neu…)! #AI4Science #AutoResearch
Article
Week of 07/20/26-07/26/26: Can you trust what a model says about what it just did?
Welcome to another weekly entry! Thank you to everyone who submitted and voted on ideas. Each idea was explored by one agent, Codex. All three runs were small pilots on small models, and Codex rated
1
Chicago HAI
@ChicagoHAI
Jul 26
Stop relying on complex latent maps to spot AI bias when asking the model directly works better✨
Chenxi Peng
@ChenxiP9458
Jul 26
Article
Week of 07/13/26-07/19/26: Can you catch AI bias by mapping concepts, or do you have to just ask?
Welcome to another weekly entry! Thank you to everyone who submitted and voted on ideas. Each idea was explored by one agent, Claude. This week we tested three things. First, can you predict what an
Chicago HAI
@ChicagoHAI
Jul 22
Built on OpenAIReview (openaireview.org) and Veritas (github.com/ChicagoHAI/ver…), SAI Review (sai.science) put ICML 2026 oral papers to the replication test!
Chenhao Tan
@ChenhaoTan
Jul 22
Article
How much science is verifiable? Results from replicating ICML 2026 oral papers
[Please find the most updated version at https://sai.science/blog/how-much-science-is-verifiable] As AI agents become capable of increasingly complex, long-horizon tasks, we have an exciting opportunity to rethink the research
Chicago HAI
@ChicagoHAI
Jul 18
🦄 for casual reasoning!
Qirun Dai
@qirun_dai
Jul 17
Introducing UniCo🦄, a data generation framework for training Universal Causal Reasoners. We show causality-centered training develops a causal mindset towards faithful and consistent reasoning in the real world. With continued SFT on 66.6K UniCo data, Qwen3 and Olmo-3-Instruct
Chicago HAI
@ChicagoHAI
Jul 12
congrats!🎉🎉🎉
Xiaoyan Bai
@Elenal3ai
Jul 12
We’re honored that our paper, “The Story is Not the Science”, received the 🏆Best Poster Award at the ICML 2026 AI for Science workshop!🍻 Check out our paper here: arxiv.org/abs/2602.18458
Quote
AI for Science
@AI_for_Science
Jul 12
😊Excited to announce the @TrillionLabs Trillion labs best poster award winners: #19 PaperDoctor: Evidence-Grounded and Actionable Feedback for Scientific Papers in Progress #193 The Story is Not the Science: Execution-Grounded Evaluation of Mechanistic Interpretability Research

Advertisement

Advertisement