A post-rigorous derivation of the Gauss-Newton matrix
Why take a Hessian when a gradient will do? || May 17, 2025
Can you train a neural network forever?
Understanding trainability in neural networks || December 27, 2023
Deep dive into the edge of stability
Making loss landscapes trendy again. || October 15, 2023
Evaluating understanding in LLMs
It's surprisingly hard. || August 27, 2023
Do we know why deep learning generalizes yet?
It depends on your epistemology. || July 30, 2022
The Importance of Making Mistakes in RL
A tale of two NeurIPS papers || December 18, 2021
How to Win Scholarships and Influence Donors
All of my thoughts on scholarships in one place || September 25, 2021
Auxiliary tasks in RL
Maybe the real reward was the representation we learned along the way. || April 3, 2021
Power to the people, but how?
From muffins to marathons || November 5, 2020
Why I'm Learning Biology
And why yoou should too || October 5, 2020
In praise of the logarithm
Why are logarithms so magical? || April 20, 2020
Causality
If causation isn't correlation, then what is it? || August 9, 2019
Probabilistic Graphical Models
Why I shouldn't quit my PhD to go into the coffee business. || November 11, 2018
A semi-coherent summary of set theory pt 2
Or how set theorists are bad at naming things || May 25, 2017
A semi-coherent summary of set theory
Or why math really really needs rules || May 20, 2017
Week 1 in Oxford
I'm in Oxford! || May 14, 2017
School starts, as do the cool proofs
Infinity is still really cool. || September 6, 2016
What Work is Worth
Or, how getting grossed out by blood was possibly the most profitable personality trait I ended up with. || August 21, 2016
First Week at Microsoft
Or how I installed more microsoft products in two days than I had in the last two years. || June 6, 2016
On Entering the Real World
Or, on getting a job at a big tech company. || May 25, 2016
A gentle introduction to infinities
Infinity is bigger than you think. || May 16, 2016
A round-up of my favourite proofs from introductory math courses
I spent a lot of time proving things this year. || April 28, 2016