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

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by pu_pe

Mon, 09 Mar 2026 17:47:58 GMT

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] https://arxiv.org/abs/2402.04494

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by pu_pe

Mon, 09 Mar 2026 17:46:04 GMT

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 because something is a next token predictor doesn't mean it cannot perform tasks that require intelligence and planning. The r in strawberry is more of a fundamental limitation of our tokenization procedures, not the transformer architecture. We could easily train a LLM with byte-size tokens that would nail those…

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by famouswaffles

Wed, 16 Apr 2025 22:07:31 GMT

>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, failing and getting a little better, rinse and repeat. Pre-training is not like reading a book. LLMs trained on chess games play chess just fine. They don't make the silly mistakes you're talking about and they very rarely make illegal moves. There's gpt-3.5-turbo-instruct which i already shared and plays at around 1800…

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by famouswaffles

Mon, 07 Apr 2025 02:14:18 GMT

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 the like simply don't care much about their LLMs playing chess. That or post training is messing things up.

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by janalsncm

Fri, 14 Mar 2025 19:14:54 GMT

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 by a small program that can run on your phone. https://arxiv.org/pdf/2402.04494

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by lxgr

Fri, 13 Dec 2024 05:00:55 GMT

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 evaluation, but it's relatively simple/lightweight in comparison to these, and it gains its strength from being used as part of deep search, rather than using a powerful/heavy neural network in a shallow tree search. [1] https://arxiv.org/html/2402.04494v1 [2] https://www.maiachess.com/

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by famouswaffles

Fri, 22 Nov 2024 16:10:22 GMT

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 turbo-instruct's chess ability all pegged it around 1800. https://x.com/GrantSlatton/status/1703913578036904431

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by motoboi

Fri, 15 Nov 2024 13:02:37 GMT

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

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by QuantumGood

Thu, 14 Nov 2024 21:42:38 GMT

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 to help humans take advantage of this (nothing there yet https://youtube.com/@DecisiveEdgeChess ). I have long taught my students that its possible to assess positions at a very high level with very, very little calculation, and this news hit me as "finally, evidence enough to intrigue more people that this is…

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by wenc

Thu, 14 Nov 2024 21:28:43 GMT

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 about using search to play chess, it can go several ways. Brute-forcing all chess moves (NP hard) doesn’t work because you need almost infinite compute power. If you use a chess engine with clever heuristics to eliminate bad solutions, you can solve it in finite time. But if you learn from the best humans performing…

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by thomasahle

Wed, 23 Oct 2024 15:30:49 GMT

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.

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by QuantumGood

Fri, 18 Oct 2024 20:02:30 GMT

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 unprecedented scale. This paper investigates the impact of training at scale for chess. Unlike traditional chess engines that rely on complex heuristics, explicit search, or a combination of both, we train a 270M parameter transformer model with supervised learning on a dataset of 10 million chess games. We annotate…

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by bob1029

Fri, 18 Oct 2024 16:07:55 GMT

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 availability for both players, a potential en passant target, a half-move clock and a full-move counter. We essentially take any variable-length field in the FEN string, and convert it into a fixed-length sub-string by padding with ‘.’ if needed. We never flip the board; the FEN string always starts at rank 1, even when…

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by famouswaffles

Fri, 06 Sep 2024 16:29:52 GMT

>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 good example, since it's easy to understand. The generative process for world class chess (whether human, or for an engine) involves way more DEPTH (cf layers) of computation than the transformer has available to model it and it's just baffling because: 1. Humans don't play chess anything like chess engines. They…

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by sorobahn

Sun, 25 Aug 2024 00:18:28 GMT

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 representations generated by the JEPA model to approximate useful Q-values [1]. This method currently has no search so I'm planning on comparing with this paper [2] which achieves GM level chess without any search. Honestly, Im unsure if the full pipeline is stable enough to even converge, but it's fun experimenting. I'm bad at…

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by salamo

Sun, 09 Jun 2024 02:26:01 GMT

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 internet even feasible. Other methods (RNNs and LSTMs) were simply too slow. Transformers are a new hammer for an internet-sized nail. If I can make an analogy to chess engines, a type of AI so old that people don't call it AI anymore [2], if we had started out by applying transformers to available chess games, we would…

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by adw

Tue, 23 Apr 2024 16:20:44 GMT

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 competitive sport), but soon enough having a human in the team made the program worse. But at least the evaluation functions were designed by humans, right? That lasted a remarkably long time; first Stockfish became the strongest engine in the world by using distributed hyperparameter search to tweak its piece-square tables…

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by janalsncm

Sun, 25 Feb 2024 03:04:45 GMT

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 questions about scaling laws for this kind of thing.

Paper and discussion history. A mention is not an endorsement.

Amortized Planning with Large-Scale Transformers: A Case Study on Chess — mentioned by matteoraso

Sun, 11 Feb 2024 07:27:08 GMT

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 months ago that's tangentially related to this topic[1]. The gist of it is that the search tree for a chess engine is the most important part, since a perfect solution for chess would just be a brute-force search of the entire game tree. Trying to get around that by building a better evaluation function is just a waste of…

Paper and discussion history. A mention is not an endorsement.

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

Thu, 08 Feb 2024 13:57:19 GMT

Grandmaster-Level Chess Without Search

198 points; 130 discussion replies on HN. Paper and source history. A submission is not an endorsement.

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

Thu, 08 Feb 2024 11:01:36 GMT

Grandmaster-Level Chess Without Search

7 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.