Day 3 continues with the oral presentations about Causality! 👉 auai.org/uai2025/schedu…

Former Colombian President Uribe’s only crime has been to tirelessly fight and defend his homeland. The weaponization of Colombia’s judicial branch by radical judges has now set a worrisome precedent.

-Christopher Landau: Una de las tendencias preocupantes de nuestro tiempo es la utilización de los sistemas judiciales como arma contra opositores políticos. Nuestras diferencias políticas deberían resolverse en las urnas, no en los tribunales. Obviamente, esto no significa que

I’m thrilled to share that the Second Edition of The Book of Why will be released at the end of this year. It will include brief discussions of recent breakthroughs in causal inference, as well as some aspects of LLMs. Join me on this next journey into the land of causality —

There is some confusion among readers of #Bookofwhy regarding the impressive "causal understanding" LLM's, which seems to defy the theoretical prediction of the Ladder of Causation. The Ladder predicts that, regardless of data size, no learning machine could correctly answer

In a recent work (causalai.net/r136.pdf), we examined whether LLMs are potential sources of probabilistic knowledge (rung 1 of Pearl's hierarchy), which led to the benchmark at llm-observatory.org. The answer was no, which was surprising and poses fundamental challenges for

I was happy to give a more technical talk on how we might create an AI at RLC-2025 and AGI-2025 (video below). The Oak Architecture: A Vision of Super-Intelligence from Experience As AI has become a huge industry, to an extent it has lost its way. What is needed to get us back on

Alternate exponent and logarithm notation brings out symmetries in properties. johndcook.com/blog/2025/05/1…

rank decomposition I updated the website how.rl.works

'Ex falso quodlibet.' From a false assumption, anything follows.

Our weekly harvest has arrived, blessed with 9 pages of exciting titles of papers in Causal Inference: ucla.in/41Vzf5C. My attention was caught by the paper on "conditional ignorability" by Elias Bareinboim and Drago Plecko causalai.net/r120.pdf. Why? Because I've been

🚨 Submissions for ALT2026 are now open! Submit your best work and join us in Toronto!🚨 Deadline: October 2 AoE Conference: Feb 23-26, 2026 algorithmiclearningtheory.org/alt2026/

We argue and demonstrate that it's wrong to say: "causal reasoning is a missing-data problem" (Holland, Rubin etc.). The opposite is true: missing-data is a causal reasoning problem. See ucla.in/3r87JMZ. Is there anyone today who advocates the former?

Unpopular opinion: When a paper has a senior mentor and a junior mentee, the senior author must make sure the claims are correct and well supported. They must check every claim and gate the submission until it meets that bar. The junior author is the generator. The senior author

“Everyone knows” what an autoencoder is… but there's an important complementary picture missing from most introductory material. In short: we emphasize how autoencoders are implemented—but not always what they represent (and some of the implications of that representation).🧵

Uncorrelated random variables are not necessarily independent.

Join leading researchers to explore the future of world models, whether you’re interested in JEPAs, RL, video generation, LLMs, robotics & beyond. Don’t miss it. ✅ Apply to attend in person: docs.google.com/forms/d/e/1FAI… 📩 Accepted applicants will receive registration details via

Yann LeCun on architectures that could lead to AGI LLMs can take us only so far. "If you are interested in human-level AI, don’t work on LLM Abandon generative models in favor joint-embedding architectures Abandon probabilistic model in favor of energy-based models Abandon

I like Larry Wasserman's quote, which separates the mathematics from the physics.

I think the obsession with randomized controlled trials as the default of "doing science" has probably set us back a few decades