My "Starting a Startup" post from a few months ago needed a refresh.
January 22, 2024
Write-up explaining an implementation of monotonic attention using a probabilistic graphical model.
November 9, 2023
A short, hand-wavy explainer for the mathematical intuition behind faster attention mechanisms.
September 16, 2023
An accessible introduction to diffusion and flow matching models.
July 19, 2023
A reference collection of fast attention implementations.
June 29, 2023
I left FAIR to start a startup a few weeks ago, and figured I should describe what we're actually doing.
June 27, 2023
In-depth explanation of the math behind the RWKV model, with PyTorch implementations, plus a discussion of numerical stability.
June 16, 2023
This post is a reference for the different types of gears that might be relevant for robotics applications.
March 6, 2023
This post is a collection of the different types of electrical connectors that might be relevant for robotics.
March 6, 2023
A list of ideas for robotics startups, focusing on things that are feasible right now and things that will likely become feasible in the next few years.
December 25, 2022
A collection of my ideas relating to robotics pre-training.
November 1, 2022
Simple overview of what a PID controller is, how it works, and how to make one yourself.
September 29, 2022
Meta-journal about journaling for more consecutive days than I initially thought I would, and whether or not it is a worthwhile habit to cultivate.
July 26, 2022
Python code snippit for doing background GPU monitoring using `nvidia-smi`
July 21, 2022
Short post with code snippits for creating videos from Numpy arrays in Matplotlib.
April 29, 2021
Reflections on our time in the United Kingdom during the Covid-19 pandemic.
December 18, 2020
The results of an experiment I've been conducting on myself.
December 2, 2020
Some functions I found useful to add to my bash and zsh profile.
May 27, 2020
A walkthrough of how to optimize the log-sum-exp function in PyTorch.
May 20, 2020
Some tricks I found useful for writing CUDA extensions for PyTorch.
May 6, 2020
There is a teacher and 2 students in a classroom. The students are A and B. The teacher thinks of 2 positive integers and tells the sum of those numbers to student A without student B hearing it. Then tells their product to student B without student A hearing it. After this, the teacher asks the 2 students what was the 2 numbers. First student A says: I don't know. Then student B says: I don't know either. After hearing this, student A says: Now I know. Then student B says: Now I know them too. What were the 2 numbers?
April 30, 2020
A combination for a lock has 3 wheels, X, Y, and Z, each of which can be set to eight different positions. The lock is broken and when any two wheels of the lock are in the correct position, the lock will open. Thus, anyone can open the lock after 64 tries (let A and B run through all possible permutations). However, the safe can be opened in fewer tries! What is the minimum number of tries that can be guaranteed to open the lock?
April 30, 2020
A comparison of Hidden Markov Models and Conditional Random Fields, two kinds of probabilistic graphical models.
April 7, 2020
Recap and potential future directions from the MIT Covid-19 Challenge.
April 5, 2020
Summary and thoughts about The Decadent Society: How We Became the Victims of Our Own Success by Ross Douthat.
March 22, 2020
A demo of how to code the Viterbi algorithm in Numpy.
March 15, 2020
Some of my thoughts about effectively controlling the elephant mind.
March 1, 2020
Exploring the Land of the Rising Sun for 19 days by train, through Tokyo, Nikko, Sendai, Sapporo, Kyoto, Osaka and Nagoya.
May 8, 2017
A field guide to traveling to Cuba, written by naive college students for naive college students, mostly as exposition.
March 4, 2017
A short post and script regarding using Gensim Word2Vec embeddings in Keras, with example code.
August 2, 2016
Building on the Recurrent RBM for sequence modeling. This post relates to what I am doing for my Master's thesis.
July 18, 2016
Narration from my trip through Nashville, Chicago, Toronto, Montreal, and Washington DC.
May 11, 2016
An in-depth introduction to using Keras for language modeling; word embedding, recurrent and convolutional neural networks, attentional RNNs, and similarity metrics for vector embeddings.
April 27, 2016
Some facts and very sarcastic opinions regarding craft beers that can be bought at the Krogers near my apartment.
March 30, 2016
A quick introduction to using Theano for deep learning, from the bare-bones to a full neural network.
February 23, 2016