Tal retweeted
My dear front-end developers (and anyone who’s interested in the future of interfaces):
I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept):
Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow
Tal retweeted
I’m very happy to present my toy research project: Sotaku!
It's a neural net that automatically discovered the rules of sudoku and learned to solve them, achieving a new state-of-the-art score of 98.9% on one of the hardest sudoku datasets, while being agnostic to the game, and beating all other sudoku-optimized neural net architectures*
Read more for fun motivations, plus some extremely unconventional discoveries, e.g. reverse curriculum consistently beating curriculum (!), emergent reasoning-like capabilities, and the future of traditional programming
I created this app for NeurIPS, mostly driven by my own desires to not feel lost 🙂
paperjam.ai/neurips25
It’s small but mighty! 🧵
Many thanks to @shlomiatar for being an awesome collaborator on this project
There’s per-paper discussions, powered by GitHub/Giscus, as well as easy navigation to authors homepages
StyleGAN is bananas
just binary_cross_entropy(EfficientNet(x)[:, classes['banana']]) to optimize StyleGAN2's input
derivative.works/
Something @_joelsimon & I collaborated on. For some reason Twitter is flagging the website (the .works domain?) as unsafe, but it makes me smile :)
New experiments that use machine learning to create generative portrait collages by cutting up and rearranging @Artbreeder images.
Interactive website & more info @ derivative.works/
Collab w/ @eiopa
Tal retweeted
Neuroevolution of Self-Interpretable Agents
Agents with a self-attention “bottleneck” not only can solve these tasks from pixel inputs with only 4000 parameters, but they are also better at generalization!
article attentionagent.github.io/
pdf arxiv.org/abs/2003.08165
Read on 👇🏼
Tal retweeted
As data scientists, we (with @math_rachel) have done our best to look at the data around covid-19, and what it means to you and your community.
Our view: it is appropriate to be very concerned, and significantly change your lifestyle, right now.
1/13
fast.ai/2020/03/09/coronavir…
Tal retweeted
a lot of ppl don't realize this, but if you have a library card, you can:
* borrow books and audiobooks on your phone/kindle/etc. for free using overdrive.com/apps/libby/
* stream movies for free on kanopy.com/
enjoy!!
Tal retweeted
You're not a rockstar. I know this is hard to hear, but you never were. A rockstar is "a person treated as a celebrity, especially in inspiring fanatical admiration". This was never your job title, and this was never a part of your job. It sounded attractive, which was the point-
Tal retweeted
Now that people have already said highly controversial stuff like ”debugger is useless for C++ development”, I think I can share my own controversial thoughts about unit testing, DRY, copy-paste coding and function length, etc... with 20 years of C++ programming experience.


















