Introducing Maia, a human-like neural network chess engine

@gloriavictis101, not sure about those numbers but there is definitely a limit on Maia's capabilities.

Maia by design is a 'weak' chess AI as it completely disregards any depth in it's prediction of the moves. It makes all of its moves only based on the current position, move history and metadata like rating and time left, but it makes no effort to calculate ahead at any depth, unlike any other chess engine, which all employ some search algorithms too calculate ahead. So there would definitely a hard limit on Maia's performance because of this.

Maia is simply designed to match moves made by humans and not necessarily make the best moves possible. And it does it amazingly well. I'm certain it could be extended above the 1900 (actually the 1900 Maia predicts human moves very well into the 2500's, better than any other engine). Making good predictions does not necessarily make it play stronger as a matter of fact they tried to include some models where they included searching of moves ahead but it made their prediction accuracy worse.

I think the main reason they did not do that would probably be best explained by this: lichess.org/stat/rating/distribution/blitz
There is just so much more data available between 1100 and 1900 to have more confidence in their actual research. The higher rated player pool becomes so small that you could introduce certain biases in your models and having a much harder time with error margins.

how can I create maia BOT

Why does the bot decline all my challenges?

I'm sorry to tell you that your "artificial intelligence" is not intelligent at all, firstly because the silly mistakes that you make, for example, leaving the queen hanging, do not compensate for the great ability you have to find unique moves or complicated dunks in a few seconds even in two seconds he makes you forced sequences, that is, he leaves the queen as a beginner but makes forced plays or mate in 5 in 6 in a few seconds as a master. When is a player seen to have the ability to find deep and forced moves and the stupidity of continually leaving the pieces behind?

This AI is amazing. But I have a feedback, which I wrote in the chat box in the game. I played maia9 and defeated it.

The bot made some obvious mistakes. And happily gave me the rook to take (which I missed, being human, of course). But I don't think a 1900 player would do such mistakes. I am 1700 plus.
But it was fun to play, and I am immensely puffed that I defeated a bot, and the highest version of it. Surely, it will help me improve my game manifold and I would be thrilled if I could make a UCI engine of it.

There are 2 BOT systems in lichess right? I.E: Stockfish and Maia

@ghetu bruh how? i dont believe it

Doesn't this just provide cheaters with a way to go undetected? If it reaches Master level then there will be no stopping people from cheating. And if it reaches GM level, what kind of potential for cheating in money tournaments is there? Seem like a very cool idea if you have a way to prevent cheating.

I m playing mala5 at bullet, it is rated 1667 and I m rated 1919. I m loosing 2 4 currently, so I don't think it plays like human enough. He doesn't blunder enough like human, he play way too fast against some move not easy to anticipate. And also a bot rated 200 below my elo shouldn't win 4 2 againt me.

@quickchess123 : Which point exactly you didn't understand?