Codex and Claude Code have a neat auto approve feature where 1) it doesn't ask for permissions, but 2) you get to feel safe. Well --- do you? The premise is it is asking an agent for permission. But if you don't trust the driver agent, why should you trust the review agent?

On Monday @ncollina.bsky.social @iraglobusharris.bsky.social and I are giving a tutorial at ICML on (multi)calibration and its applications. You can find slides and an annotated bibliography on the website: calibration-tutorial.github.io as well as an interactive demo of online calibration algs.

Calibration, Decisions, and Collaboration in Learning | ICML 2026

An ICML 2026 tutorial on making probabilistic predictions trustworthy for downstream decision-making and collaboration.

calibration-tutorial.github.io

Are you at ICML next week? Feel like your decision-making for which sessions to attend might not be risk minimizing? Don't incur (swap) regret and come to my, @aaroth.bsky.social, and @ncollina.bsky.social's tutorial Monday on multicalibration, decision-making, and collaborative learning!

Excited to give a tutorial this year at ICML 2026!

ICML Conference@icmlconf.bsky.social · 6mo ago

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...

If someone refers an undergraduate student to a known sex offender for a job, and includes a comment about how good-looking the student is in their recommendation letter, that someone should never be allowed to teach undergraduate students ever again.

Why do I have to pretend that I'm going to print something in order to save it as a PDF. Why do I have to engage in a little ruse.

Heard joke once: Man goes to doctor. Says he's depressed. Says life seems harsh and cruel. Says he feels all alone in a threatening world where what lies ahead is vague and uncertain. Doctor says, "Sorry: you have exceeded your token usage. Please try again later or switch to Auto"

Tomorrow's front page of the Minnesota Star Tribune: Jan. 24, 2026

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.

You and your wife drop your 6-year-old off at school. You just moved here. You see ICE terrorizing your new neighbors. You film them, as is your legal right. Your wife complies with orders. She is then shot in the head. You still have to pick up your child later today. This could be you.

A message for you all to carry through the year

I just think it would be neat if turkeys used the same technique to draw us

📢 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...

TCS+ RSVP: Natalie Collina (2025/12/03)

Title: Swap regret and correlated equilibria beyond normal-form games

forms.gle

We have progressed from data collection to data analysis.

Halloween logicals, still the best 10/31 venn

Nature’s Gold, England’s Glory

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

Natalie Collina@ncollina.bsky.social · 12mo ago

Our paper on algorithmic collusion was featured in a Quanta article! www.quantamagazine.org/the-game-the...

Our paper on algorithmic collusion was featured in a Quanta article! www.quantamagazine.org/the-game-the...

The Game Theory of How Algorithms Can Drive Up Prices | Quanta Magazine

Recent findings reveal that even simple pricing algorithms can make things more expensive.

quantamagazine.org

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

Aaron Roth@aaroth.bsky.social · 2y ago

Suppose you and I both have different features about the same instance. Maybe I have CT scans and you have physician notes. We'd like to collaborate to make predictions that are more accurate than possible from either feature set alone, while only having to train on our own data.

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.

Thing with Grok is that better versions will be less overt and more convincing. An expert on arguing about the deficit, immigration, public health, etc. with a particular political slant

As AI systems continue to become more complex and hard to reason about, one increasingly powerful lens through which to understand them is through the incentives of AI creators.

Eugene Vinitsky 🍒@eugenevinitsky.bsky.social · last yr.

Well, they finally pulled it off. Grok parrots propaganda as requested

Ecstatic and deeply honored by this award. I've had great fun thinking about algorithms as strategies for repeated games over the past few years and hope that this highlight will push more researchers to come up with exciting directions in this field! Come to our talk on Monday to learn more!

Natalie Collina@ncollina.bsky.social · last yr.

Delighted (and honestly a little bit stunned) that our paper “Swap Regret and Correlated Equilibria Beyond Normal-Form Games” was just awarded both the “Best Paper” and “Best Student Paper” at EC! arxiv.org/abs/2502.20229

This best paper news is a good opportunity to highlight that a month or so ago I started maintaining CV of failures on my website. It will almost certainly continue to grow linearly in the number of things I attempt to do, and that’s a good thing! www.seas.upenn.edu/~ncollina/Fa...

Delighted (and honestly a little bit stunned) that our paper “Swap Regret and Correlated Equilibria Beyond Normal-Form Games” was just awarded both the “Best Paper” and “Best Student Paper” at EC! arxiv.org/abs/2502.20229

Swap Regret and Correlated Equilibria Beyond Normal-Form Games

Swap regret is a notion that has proven itself to be central to the study of general-sum normal-form games, with swap-regret minimization leading to convergence to the set of correlated equilibria and...

arxiv.org

Harriet Tubman #quilt by my Mom, Vera P. Hall, who makes quilts celebrating Black people who fought for their own freedom. This seems to be the crowd favorite of the “We Didn’t Wait for Freedom” series. Happy #Juneteenth #quilting

NEW: Democracy is alive in Philly! Amazing scenes in Philadelphia as thousands hit the streets for the anti-Trump protest. #NoKings #50501Movement

I hugely recommend Harry as a researcher, mentor and person. If you are interested in the stuff he does, apply to do a PhD with him!

Harry Goldstein@harrisongoldste.in · last yr.

If you are considering applying for a PhD this Fall, please get in touch. I’m looking for students who are interested in PL, SE, and/or HCI — and ideally all three! You can find more information about me and my work on my website: harrisongoldste.in

Check out the terrific set of EC 2025 accepted papers! ec25.sigecom.org/program/acce...

The idea that you can just “teach computer science” and be apolitical is a beautiful dream that expired in the 2000s, at the latest. Computer science has re-organized every facet of our society: it is inherently political. Instead of taking this idea seriously, we ran from it. Now we live in hell.