Discrete Diffusion: Continuous-Time Markov Chains · May 22, 2025

We may finally crack Maths. But should we? · June 8, 2023

Mortal Komputation: On Hinton's argument for superhuman AI. · May 30, 2023 · AGI opinion

Autoregressive Models, OOD Prompts and the Interpolation Regime · March 30, 2023

We May be Surprised Again: Why I take LLMs seriously. · March 22, 2023

Implicit Bayesian Inference in Large Language Models · March 3, 2022

Eastern European Guide to Writing Reference Letters · February 28, 2022

Causal inference 4: Causal Diagrams, Markov Factorization, Structural Equation Models · June 10, 2021 · causal inference

On Information Theoretic Bounds for SGD · April 23, 2021 · generalization information theory

Notes on the Origin of Implicit Regularization in SGD · April 1, 2021 · deep learning generalization SGD differerntial equations