Why do all LLMs predict 27 as their favorite number? There may be a principled explanation. Learn more at Agents in the Wild at #ICLR2026. @ericeaton.bsky.social, me, @surbhigoel.bsky.social, @mkearnsphilly.bsky.social, @aaroth.bsky.social, @sikatasengupta.bsky.social, @optimistsinc.bsky.social

How many samples do you need from an unknown distribution in order to train a model with multicalibration error at most epsilon? Answer: 1/epsilon^3 samples is both necessary and sufficient.

April is #AIMonthAtPenn! On 4/24, Warren Center faculty affiliate Aaron Roth will give the George H. Heilmeier Faculty Award Lecture in Amy Gutmann Hall. More information and registration here: ai.upenn.edu/heilmei...

Say hi to @marcelhussing.bsky.social at ICLR

I've recently been getting invitations to talk about how to use AI tools to assist with TCS research. Its something I've been doing a lot, but don't have structured thoughts about how to explain process. But I'm going to try -- first such talk is tomorrow: t.co/wlHPBzXzDm

AI Agents like Codex are very good at figuring out taxes, including obscure local ones that Intuit doesn't bother with (looking at you, Philadelphia local taxes). Businesses that provide financial/legal services that involve reasoning through dense but public documentation are in trouble.

Announcing the #ICML2026 tutorials! All ten tutorials will be presented the first day of the conference, Monday July 6. Read the blog post for more details on the selection process! blog.icml.cc/2026/04/02/a...

So many interesting things here. (N.b. I get to think ab interfaces for this this all day long at work :)) One thing I find interesting here is how similar the real work of science is to that of the humanities, both of which are centered around human judgement ab what is relevant and interesting.

Alpha_0 joke from Dogman

Very cool work. Empirical science has many researcher-degrees-of-freedom which makes it hard to interpret specific studies --- these are only a single trajectory through the data analysis multiverse. Human researchers are opaque. But with agents you can explore the whole space!

Neural networks are highly non-convex, so approximate error minimizers need not look anything like each other in parameter space. But we show that nevertheless (for many model sizes) approximate error minimizers must closely agree in function/prediction space despite this!

Michael @mkearnsphilly.bsky.social ) and I wrote a blog post about our experiences using AI for research, and our thoughts on what these developments will mean for research, publication, and education: www.amazon.science/blog/how-ai-...

AI is bringing a sea change in scientific research methodology, training, and peer review. Amazon Scholars and Penn professors @mkearnsphilly.bsky.social and @aaroth.bsky.social on what agentic AI tools mean for the next generation of researchers.

Michael @mkearnsphilly.bsky.social ) and I wrote a blog post about our experiences using AI for research, and our thoughts on what these developments will mean for research, publication, and education: www.amazon.science/blog/how-ai-...

Which is the better model for math? GPT 5.2, or GPT 5.3 codex (either one on high reasoning)?

Sometimes you gotta split the difference. From Aaron Roth's (@aaroth.bsky.social) plenary talk at #ALT2026

Did you just miss punching your ticket to Rio or Salt Lake City? Wanna go to a conference where people will engage with you and your paper on foundations of responsible computing, and you won't get lost in the crowd? Submit to #FORC2026, in Boston in June! Deadline in 2 weeks.

The other paper accepted to @iclr-conf.bsky.social 2026 🇧🇷. Our work on replicable RL sheds some light on how to consistently make decisions in RL. @ericeaton.bsky.social @mkearnsphilly.bsky.social @aaroth.bsky.social @sikatasengupta.bsky.social @optimistsinc.bsky.social

I try to avoid posting about politics here, but I feel compelled to say some things that should be obvious: 🧵

The NSF has played a key role in American science, and risks being collateral damage in the war against science. #econsky #academicsky #NSF #science marketdesigner.blogspot.com/2026/01/hist...

The paper is here: arxiv.org/abs/2601.05245 Its joint work with @ncollina.bsky.social, Jiuyao Lu, and George Noarov. Natalie and George are on the job market --- check them out. www.seas.upenn.edu/~ncollina/ noarov.com

Excited about a new paper! Multicalibration turns out to be strictly harder than marginal calibration. We prove tight Omega(T^{2/3}) lower bounds for online multicalibration, separating it from online marginal calibration for which better rates were recently discovered.

Yes. We already have a set of ingrained red flags for human written papers that signal a lack of care: not citing the relevant literature, not formatting or typesetting math correctly, etc. These don't mean the paper is wrong but they strongly correlate with lack of care. But...

Getting absurd over at the ACM…

2025 was an eventful/disruptive year for computer science research, for two reasons: 1) a shock to federal funding, and 2) the arrival of AI models capable enough to assist mathematical research. 1) is unambiguously bad and 2) is probably mostly good. I'll write about AI first.

📢 Our last TCS+ talk of the season will be Wed, Dec 3 (10am PT, 1pm ET, 19:00 CET): Natalie Collina (@ncollina.bsky.social), from UPenn, will tell us about "Swap regret and correlated equilibria beyond normal-form games"! RSVP to receive the link (one day before the talk): forms.gle/utLgSxLpqvpx...

I am recruiting PhD students at NYU Courant to conduct research in learning theory, algorithmic statistics, and trustworthy machine learning, starting Fall 2026. Please share widely! Deadline to apply is December 12, 2025.

Did your fairness/privacy/CS&Law/etc paper just get rejected from ITCS? Oh FORC! Submit tomorrow and join us at Harvard this summer.

Foundations of Responsible Computing (FORC) is a super exciting new conference focused on the intersection of mathematical research and society. It's also a fantastic and vibrant community. Check out the CfP, with two deadlines. Also follow the new BSky account @forcconf.bsky.social !

The first of two @forcconf.bsky.social 2026 deadlines is tomorrow, Nov 11! I hope everyone is putting finishing polishes on their submissions. For everyone else who doesn't want to miss out on the fun at Harvard this summer, there is another deadline in Feb. responsiblecomputing.org/forc-2026-ca...

If you work at the intersection of CS and economics (or think your work is of interest to those who do!) consider submitting to the ESIF Economics and AI+ML meeting this summer at Cornell: www.econometricsociety.org/regional-act...

A few weeks ago everyone was super hype about Nano Banana. Meanwhile, I ask it to do super basic things and it fails. What am I doing wrong?? (why would I want a collage of these amazing researchers? Stay tuned CC @let-all.com 👀) More fails in the transcript: gemini.google.com/share/5cc80f...

Announcing the 7th Learning Theory Alliance mentoring workshop on November 20. Fully free & virtual! Theme: Harnessing AI for Research, Learning, and Communicating Ft @aaroth.bsky.social @andrejristeski.bsky.social @profericwong.bsky.social @ktalwar.bsky.social &more

I've been enjoying learning about linear regression. This is a really cool machine learning technique with some really elegant theory --- someone should have taught me about this earlier!

How should you use forecasts f:X->R^d to make decisions? It depends what properties they have. If they are fully calibrated (E[y | f(x) = p] = p), then you should be maximally aggressive and act as if they are correct --- i.e. play argmax_a E_{o ~ f(x)}[u(a,o)]. On the other hand

If you are around Berkeley today stop by Evans 1011 for a talk: events.berkeley.edu/stat/event/3...

Congrats to @epsilonrational.bsky.social @ncollina.bsky.social @aaroth.bsky.social on being featured in quanta! (Also do check out the paper, also involving Sampath Kannan and me that the piece is based on here: arxiv.org/abs/2409.03956)

And now might be a good time to mention, I’m on the faculty job market this year! I do work in human-AI collusion, collaboration and competition, with an eye towards building foundations for trustworthy AI. Check out more info on my website here! Nataliecollina.com

(And Natalie is on the job market..)

If you are at Johns Hopkins tomorrow stop by --- also on Zoom: hub.jhu.edu/events/2025/...

An interesting debate between Emily Bender and Sebastien Bubeck: www.youtube.com/watch?v=YtIQ... ---Emily's thesis is roughly summarized as: "LLMs extrude plausible sounding text, and the illusion of understanding comes entirely from how the listener's human mind interprets language. "

Announcing (w @adamsmith.xyz @thejonullman.bsky.social) the 2025 edition of the Foundations of Responsible Computing Job Market Profiles! Check out 40 job market candidates in mathematical research in computation and society writ large! Link: drive.google.com/file/d/1zvsr...

Join us on October 23 for our next Gerald M. Masson Distinguished Lecture, featuring @upenn.edu’s @aaroth.bsky.social! Learn more here: www.cs.jhu.edu/event/gerald...

The FORC 2026 call for papers is out! responsiblecomputing.org/forc-2026-ca... Two reviewing cycles with two deadlines: Nov 11 and Feb 17. If you haven't been, FORC is a great venue for theoretical work in "responsible AI" --- fairness, privacy, social choice, CS&Law, explainability, etc.

One more thought: AI tools are a very useful research accelerator for an expert, and I plan to use them whenever I can. But at the moment it is very easy to be led down false paths if you let them get ahead of yourself and lure you too far from your expertise.

To contribute to common knowledge :-) I too have been integrating AI tools closely into my research. This paper arxiv.org/abs/2507.09683 with @mkearnsphilly.bsky.social and Emily was my first experiment with this, and it was just accepted to SODA. I'll describe the process in thread.

Appearing in SODA 2026! Last year we had a 3-page SODA paper, this one is 107 pages. Next time I’m thinking we swing way back the other way and just submit a twitter/bluesky thread

The opportunities and risks of the entry of LLMs into mathematical research in one screenshot. I think it is clear that LLMs will make trained researchers more effective. But they will also lead to a flood of bad/wrong papers, and I'm not sure we have the tools to deal with this.

Aligning an AI with human preferences might be hard. But there is more than one AI out there, and users can choose which to use. Can we get the benefits of a fully aligned AI without solving the alignment problem? In a new paper we study a setting in which the answer is yes.