Max Weichart

"The only thing necessary for the triumph of evil is that good men do nothing."

Developer

[Max Weichart @MaxWeichart]

@AlexWeichart @yacineMTB @pangram slop?

[Max Weichart @MaxWeichart]

Suggestion for @perplexity_ai: make top links show up instantly (< 200ms, like Google), while LLM output is loading. That way, one could use it as a full Google replacement, currently loading time for top links is just too long to be competitive (> 1000ms)

[Max Weichart @MaxWeichart]

Interested in RL? I'm planning to assemble a new online meetup, focused on reinforcement learning paper discussions. You can sign up, and as soon as enough people are interested, you'll get an invitation.

More information and registration: https://t.co/3j2LTyT1nZ

[Max Weichart @MaxWeichart]

@paddlepaddle_ No problem. Could you please create a GitHub issue with a problem description (if possible reproducible) and I will help you out! https://t.co/QK8Z4WgQVn

[Max Weichart @MaxWeichart]

🎉Today marks the first release of Tetris Gymnasium! If you're an RL researcher or just somebody who wants to get into it, give it a look! You can start with ~5 lines of code and maybe create the next big RL algorithm!

pip install tetris-gymnasium

https://t.co/rkFwaMAoU8

[Max Weichart @MaxWeichart]

You can find me on https://t.co/ZJhvt1kLa6

[Harris Chan @SirrahChan]

@YouJiacheng Good catch! I updated the diagram here. The way the paper phrased exploring several approaches made it unclear if all or only some of the tricks were used for the cold start data. But probably the R1-Zero outputs were indeed used.

[Max Weichart @MaxWeichart]

@iScienceLuvr I lost count how many papers are called "xyz Is All You Need" by now

[Max Weichart @MaxWeichart]

This is a really thought-provoking view on LLMs that I'd like more people to talk about!

[Kyle Cranmer @KyleCranmer]

An interesting and enjoyable read from Léon Bottou and Bernhardt Schölkopf. It suggests different analogies and metaphors for framing what's going on with large language models through the imagery of Jorge Luis Borge, e.g: Fiction Machines & Vindications
https://t.co/PAflcuyChV

[Max Weichart @MaxWeichart]

@Spideraxe30 I feel like the problem with this rune is that it has to be balanced around the 1% best ults in the game and won't be viable for anyone else

[Max Weichart @MaxWeichart]

@daniela_muntyan Thanks for sharing!

[Max Weichart @MaxWeichart]

Tetris Gymnasium x Jax JIT is coming along well...

[Max Weichart @MaxWeichart]

Sorting an array with a neural network isn't as trivial as one might expect!

https://t.co/eGgKefUWRz

[Max Weichart @MaxWeichart]

@ylecun @karpathy Boltzmann left the chat

[Max Weichart @MaxWeichart]

@RaphaelWimmer The real CoT is hidden from the user, and we only see a model-generated summary. Ofc there are no details on how this process works exactly, but I can imagine there are multiple moving parts that can lead to weird output like this...

https://t.co/LSSSibGSCH

[ₕₐₘₚₜₒₙ @hamptonism]

Students at Stanford have built alphaXiv, an open discussion forum for arXiv papers. Think of it as 𝕏 for research.

[Max Weichart @MaxWeichart]

Got my first PR + bounty for @__tinygrad__ accepted today 🎉 I recommend giving it a try, maybe you can make a contribution too https://t.co/jCZrOthNby

[Max Weichart @MaxWeichart]

@MKBHD Interesting take to just close the eyes on what's happening with GenAI instead of doing something about it

[Max Weichart @MaxWeichart]

NOW you have my attention