How to make an adversary resistant neural networkI previously pontificated about the difficulties of making a neural network robust in the adversarial model and a general approach to…Jan 31, 2021Jan 31, 2021
You’re doing computer chess game commentary wrongComputer chess games are fun to play over, even if it’s just because you know that these are the best chess playing entities in the world…Jan 24, 2021Jan 24, 2021
Gardens of EdenSince John Horton Conway passed a few days ago now might be a good time to write up my thoughts on gardens of eden in his life automata.Apr 16, 2020A response icon1Apr 16, 2020A response icon1
Neural Networks as we know them are fundamentally flawed.This paper gives some technical attacks on neural networks.Sep 13, 2019Sep 13, 2019
Play much better Poker with this one weird trickI’m going to propose a completely insane way of playing better Poker, but hear me out.Jun 29, 2019Jun 29, 2019
Alphazero’s real secret sauce is MCTSAlphazero defeated Stockfish in a series of remarkable games marking, according to the common interpretation, a turning point where…Dec 21, 2017A response icon5Dec 21, 2017A response icon5
Clean Up Your StateThere’s one overriding principle of doing imperative programming safely, which experienced programmers should all have long since learned…Jun 23, 2016A response icon1Jun 23, 2016A response icon1
Donald Trump is a DoucheI’ve configured my browser to replace all instances of the word ‘leadership’ with ‘douchery’. While this makes business commentary much…Apr 25, 2016Apr 25, 2016
Double Billing is not ‘Healthy Competition’Let’s say that you’re running a company and want to create some internal competition between teams to see which ones can perform better…Feb 13, 2016A response icon11Feb 13, 2016A response icon11
Whiny RagequittingI characterized Mike Hearn’s farewell essay as a ‘whiny ragequit’. I did this because it is, well, a whiny ragequit. He attempted a hostile…Jan 16, 2016A response icon16Jan 16, 2016A response icon16
