Jerome Etienne

Level Unlocked! 🔑 Spent the night diving deep into the UCI Protocol (Universal Chess Interface). This is the secret handshake—the standard that lets you chat with any #chess engine via stdin/stdout. Suddenly, building my own engine feels a whole lot more real! Standard achieved. 👑 #buildInPublic

im vibe coding alpha zero!!! #chess #buildInPublic

A neural network model on its own cannot produce a reasonable move, as it lacks the depth of calculation required. #chess #buildInPublic

#chess fun, using fishtest pgn files (aka the chess game done by stockfish during testing), i found a "+M77" which means stockfish is evaluating that it will do Mate in 77 moves.... This is depth in the sea of chess 🤪🐳⚓ #buildInPublic

OK tonight im learning the FEN specs #chess #builtInPublic en.wikipedia.org/wiki/Forsyth...

Coding a #chess in pytorch... how come there is no early stopper in pytorch... everybody has to recode its own... #buildInPublic

Raise your hand if you code enough #chess to be able to be able to encode a board in FEN by hand 🙋‍♂️🖖

Fun in #Chess 🎉 #Stockfish is crashing when you send it a position which is illegal (e.g. invalid castling rights)... and i means crashing, not returning an error... Gasp 😜

GitHub - jeromeetienne/chess_bot.ml: using machine learning to do a chess bot using machine learning to do a chess bot. Contribute to jeromeetienne/chess_bot.ml development by creating an account on GitHub.

For those interested, it is all happening on this repo!

github.com/jeromeetienn...

Progress in my #chess model 🎉, real happy about the result 😀

Note how the training loss is above the validation loss, this is due to a nice balance between the learning rate scheduler and the dropout probability. This means it fight against overfitting efficiently ❤️

More on chess via ML tomorrow!

Tonight i learned Monte Carlo Tree Search (MCTS), a nice way to handle AI, where AI doesn't understand the game it is playing, it just play it randomly... More powerfull that it seems at first 😀

I coded a tictactoe, connect4 and othello in the everning. It is that fast.

github.com/jeromeetienn...

YouTube video by Bug How Monte Carlo Tree Search Changed AI Forever

Best video to understand how alpha-go use machine learning to become the best #chess computer! 4min tottaly worth it 👍

www.youtube.com/watch?v=2Hv4...

The chess game by Giulio Campi.

In #Renaissance culture chess was progressively considered on par with poetry, music, literature and art & therefore an eminently suitable activity for a cultivated family, like the Anguissolas, to be engaged in.

Read more: bit.ly/46eI1yj

🗃️ #arthistory #chess #skystorians #earlymodern #art

Coding #chess bot with machine learning is a good application. Especially if chess is your hobby.

learning that transformer and self attention can be applied to spatial information like chess. Usually they are used for language and time series, and for their ability to model sequences over time. #chess

This ML #chess bot seems very good at the begining of the game... if i keep only the 20 first move, it predicts the same as stockfish 95% of the time... a little too good to be true 😱

Or maybe the bot has just learned all the opening..

When coding a machine learning chess bot, it is possible to paste the PGN of the bot game into chess.com and make it estimate the ELO.

It estimate 1500 ELO but got 5 blunders... the 5 blunders are worry some 😜

#chess

Look ma, the bot is able to make a few moves! #chess

Ascii visualisation ftw 😜

GitHub - jeromeetienne/chess_bot.ml: using machine learning to do a chess bot using machine learning to do a chess bot. Contribute to jeromeetienne/chess_bot.ml development by creating an account on GitHub.

Early chess bot using pytorch - github.com/jeromeetienn...

a poster for dexter 's laboratory shows a cartoon character playing chess ALT: a poster for dexter 's laboratory shows a cartoon character playing chess

Starting to code a machine learning chess bot... whish me luck 😀

Maat - Wikipedia

Clearly, the first time i saw it was in -2500 BCE... the 42 law of maat en.wikipedia.org/wiki/Maat

hey, i did some on time series applied to the industrial field. when applied to telemetry, one can get interesting stuff. e.g. predictive maintenance, or energy disambiguation.

Big words on simple concepts

i would love to test

Similarly if i add an image on the post, it get rejected above a given limit. The doc says 1mbyte, but if the image is 150kbyte the post get rejected, so i limit them to 100kbyte. i havent done the work to actually know the limit.

Are you sure about that ? i do have 299 in my code, and 300 make the post rejected by the server.

btw i wondered why limit it to 299 and not to 300... Thinking maybe a \0 at the end for a C implementation of string... anybody actually know ? @bsky.app ?

i just saw that today when i logged in @bsky.app ... It tooks me 5min wall clock to get it 😜

Nice one!

Very true

oh yeah as i do everyday, but i admit i wont fit in this picture, i code all night, sitting on the ground with a laptop.

i dont spend money/energy for a large office and a large screen. I focus on productivity and efficiency. No in-person meeting, which induce commuting.