Amortized Planning with Large-Scale Transformers: A Case Study on Chess

There are chess engines based on transformers, even DeepMind released one [1]. It achieved ~2900 Elo. It does have peculiarities for example in the endgame that are likely derived from its architecture, though I think it definitely qualifies as an example of the fact that simply…

pu_peMar 9, 2026View on HNParent context

I meant trivial in the sense it's a solved problem, I'm sure it still costs a non-negligible amount of money to train it. See for example the chess transformer built by DeepMind a couple of years ago which I referred to in a sibling comment [1]. [1]…

pu_peMar 9, 2026View on HNParent context

>These models cannot even make legal chess moves. That’s incredibly basic logic, and it shows how LLMs are still completely incapable of reasoning or understanding. Yeah they can. There's a link I shared to prove it which you've conveniently ignored. LLMs learn by predicting…

famouswafflesApr 16, 2025View on HNParent context

That might be overstating it, at least if you mean it to be some unreplicable feat. Small models have been trained that play around 1200 to 1300 on the eleuther discord. And there's this grandmaster level transformer - https://arxiv.org/html/2402.04494v1 Open AI, Anthropic and…

famouswafflesApr 7, 2025View on HNParent context

I am an MLE not an expert. However, it is a fundamental problem that our current paradigm of training larger and larger LLMs cannot ever scale to the precision people require for many tasks. Even in the highly constrained realm of chess, an enormous neural net will be outclassed…

janalsncmMar 14, 2025View on HNParent context

There are several neural network based engines these days, including one that does exclusively what you describe (i.e. "patterns only", no calculation at all), and one that's trained on human games. Even Stockfish uses a neural network these days by default for its positional…

lxgrDec 13, 2024View on HNParent context

In Google's paper, then titled "Grandmaster level chess without search", they evaluate turbo-instruct to have a lichess Elo of 1755 (vs bots) https://arxiv.org/abs/2402.04494 Admittedly, this isn't really "the source" though. The first people to break the news on…

famouswafflesNov 22, 2024View on HNParent context

I suppose you didn't get the news, but google developed a LLM that can play chess. And play it at grandmaster level: https://arxiv.org/html/2402.04494v1

motoboiNov 15, 2024View on HNParent context

A recent discovery showing that computer chess (which was traditionally based on searching a combinatorial space, i.e. NP-hard) that is instead now being solved with transformer models, is actually playing better at the ELO level. https://arxiv.org/pdf/2402.04494 If you think…

wencNov 14, 2024View on HNParent context

The news that got my attention was https://arxiv.org/html/2402.04494v1 "Grandmaster-Level Chess Without Search" and an engine using this approach exceeding 2900 on Lichess (against humans) and over 2200 against engines. I actually started a chess channel a couple of hourse ago…

QuantumGoodNov 14, 2024View on HNParent context

So I guess when LLMs play chess at 2800 ELO (https://arxiv.org/pdf/2402.04494) they are just taking a vote on what top grand masters would play in the given position. I wonder how you would explain it when they play above any human level.

thomasahleOct 23, 2024View on HNParent context

https://arxiv.org/abs/2402.04494 > Board states s are encoded as FEN strings which we convert to fixed-length strings of 77 characters where the ASCII-code of each character is one token. A FEN string is a description of all pieces on the board, whose turn it is, the castling…

bob1029Oct 18, 2024View on HNParent context

This repository provides an implementation of our paper Grandmaster-Level Chess Without Search. https://arxiv.org/abs/2402.04494 The recent breakthrough successes in machine learning are mainly attributed to scale: namely large-scale attention-based architectures and datasets of…

QuantumGoodOct 18, 2024View on HNParent context

>An LLM will learn what it CAN (and needs to to reduce the loss), but not what it CAN'T. How difficult is that to understand?! Right and the point is that you don't know what it CAN'T learn. You clearly don't quite understand this because you say stuff like this: >Chess is a…

famouswafflesSep 6, 2024View on HNParent context

Experimenting applying Meta's V-JEPA [0] architecture for representation learning to chess. One of the challenges is that validating if the model is learning useful dynamics of the game, so I'm using it as an excuse to learn some reinforcement learning by using the…

sorobahnAug 25, 2024View on HNParent context

What transformers have taught us is that gobbling up the whole internet can get you pretty far, but it doesn't change the fundamentals. Hallucinations still are trivial [1] to elicit. On the other hand, transformers are a software breakthrough that made training on the whole…

salamoJun 9, 2024View on HNParent context

People have advanced that argument a lot, and it's often worked for a short while; then the statistical models get better. Chess was a game for humans. It was very briefly a game for humans and machines (Kasparov had a go at getting "Advanced Chess" off the ground as a…

adwApr 23, 2024View on HNParent context

I’m curious about the comparison between NNUE and the LLM-based model that Deep Mind announced a couple of weeks ago (https://arxiv.org/pdf/2402.04494.pdf). Using NNUE only (i.e. depth 1 search) would be directly comparable. If Deep Mind’s model is better it raises interesting…

janalsncmFeb 25, 2024View on HNParent context

The big problem with that paper is that grandmaster level chess is actually really bad for a chess bot. Its elo is a full 400 lower than Stockfish[0], which is the same distance between a grandmaster and a very strong untitled player. Oddly enough, I wrote a blog post a few…

matteorasoFeb 11, 2024View on HNParent context