Posts
subscribe via RSS or via Email

Can LLMs Critique and Iterate on Their Own Outputs?

How Can We Make Robotics More like Generative Modeling?

All Roads Lead to Rome: The Machine Learning Job Market in 2022

Haikus about Effective Altruism

Ranking YC Companies with a Neural Net

Leaving Google Brain ✌️

To Understand Language is to Understand Generalization

Just Ask for Generalization

Robots Must Be Ephemeralized

ML Mentorship: Some Q/A about RL

Stonks are What You Can Get Away With

Sovereign Arcade: Currency as HighMargin Infrastructure

Science and Engineering for Learned Robots

Don't Mess with Backprop: Doubts about Biologically Plausible Deep Learning

How to Understand ML Papers Quickly

Software and Hardware for General Robots

My Criteria for Reviewing Papers

Chaos and Randomness

Free Office Hours for NonTraditional ML Researchers

Three Questions that Keep Me Up at Night

Selected Quotes from "The Dark Ages of AI Panel Discussion" (1984)

Differentiable Path Tracing on the GPU/TPU

Robinhood, Leverage, and Lemonade

Tips for Training Likelihood Models

Normalizing Flows in 100 Lines of JAX

Lessons from AI Research Projects: The First 3 Years

Fun with Snapchat's Gender Swapping Filter

What I Cannot Control, I Do not Understand

MetaLearning in 50 Lines of JAX

Thoughts on the BagNet Paper

Uncertainty: A Tutorial

Dijkstra's, in Disguise

Bots and Thoughts from ICRA2018

Aesthetically Pleasing Learning Rates

Teacup: A Short Story

Doing a Concurrent Masters at Brown

Normalizing Flows Tutorial, Part 2: Modern Normalizing Flows

Normalizing Flows Tutorial, Part 1: Distributions and Determinants

Gamma Correction

Expressivity, Trainability, and Generalization in Machine Learning

Strong AI Ideas in Crystal Nights (Greg Egan, 2009)

Summary of NIPS 2016

Tutorial: Categorical Variational Autoencoders using GumbelSoftmax

How Can a Deep Neural Network with ReLU Activations Approximate any Function?

Riemann Summation and Physics Simulation are Statistically Biased

Monte Carlo Variance Reduction Techniques in Julia

A Beginner's Guide to Variational Methods: MeanField Approximation

Adversarial Exploration Policies for Robust Model Learning

Understanding and Implementing Deepmind's DRAW Model

Generative Adversarial Nets in TensorFlow: Part I

My Internship Experiences at Pixar, Google, and Two Sigma

ReverseEngineering Apps: a StepbyStep Beginner's Guide