Compressing Neural Networks To See If They Learn
I’ve been thinking about the paper Understanding Deep Learning Requires Rethinking Generalization.
Practical Benefits of Reading Fiction
Fiction gives concrete examples of abstract lessons, and your brain doesn’t care if it’s made up.1
-
A lot of these benefits can also be gotten from thinking deeply ↩
Book Notes: Decisive by Chip and Dan Heath 1
This book is about making better decisions. Unlike most books with that theme, it emphasizes thinking rationally.
Don't Fetishize Your Captors
See SMBC and Nick Bostrom for a longer version of my views.
How to Run Jupyter over SSH
Use port forwarding.
One-Handed Pottery
TLDR abstraction isn’t free or always desirable.
Memories True to Roads Anew: Dragonfruits and War Museums
Did you know Vietnamese has never had its own native alphabet? They were all based off Chinese characters.
Reward Hacking: 2nd Grade Kickball
Misalignment is when the reward function you specify induces an optimal policy that you don’t like. At least that’s how I define it.
Using Exponents to Teach 3 Basic Algebraic Structures
You can think of semigroups, monoids, and groups as the minimal structures needed to define and extend exponents.
Jaynes Notes 1
This is an opinionated and incomplete book. These are sloppy notes.
Memories True to Roads Anew: Skewers
Beijing does 1 thing better than anywhere else I’ve been to: skewers.
Mental Models and Tetris
Knowing lots of facts without anything to unite them is like having a crappy Tetris board.