Is the author only running their model against one benchmark? I don't think anyone finds that difficult to achieve, the difficulty comes when you want to make the model not benchmaxxed to a specific benchmark, and generalize so it can solve problems not part of the training data, but seems this model is specifically for not this? How useful is that?

If you just wanted to pass these specific tasks in this specific benchmark, and wanted to do so cheaply, I'm sure a non-LLM-based approach would yield better results for even cheaper, since what the author's model does, seem to basically be "solve ARC puzzles", not a general LLM or "coding" LLM.

▲

bkaae an hour ago | parent | next [-]

I read this as a response to the current hype around LLMs. He is showing computers can solve these issues, without using an LLM architecture. A lot of people have sort of forgot that machine learning is more than just LLMs these days.

I found it to be a very interesting angle.

▲

embedding-shape an hour ago | parent [-]

> He is showing computers can solve these issues, without using an LLM architecture.

Isn't it a LLM he's building though? My very point is that this particular use case could be solved better without building a LLM, now you claim he is not? The description of what he's doing surely makes it sound like it's a (very small) LLM, and personally I'm still on the "if it quacks like a duck" train in life.

> A lot of people have sort of forgot that machine learning is more than just LLMs these days.

Yeah, which I guess if you make my previous comment more concise, is exactly what I state too.

▲

dakolli 38 minutes ago | parent [-]

Nowhere does he say he built an llm. Hes using a transformer, not an llm.

▲

embedding-shape 34 minutes ago | parent [-]

> Nowhere does he say he built an llm. Hes using a transformer, not an llm.

Please describe what in your mind a "LLM" is exactly, then describe what this person is building. To me this sounds like "He's not building a calculator, he's just building a program that can do addition, minus, multiplication and division and display the results".

Obviously it's not a Large Language Model, but to me this looks more like a LLM than not, given the architecture he's chosen. But again, maybe I misunderstand?

▲

evilmathkid 28 minutes ago | parent | next [-]

Its not an LLM if there's no pretraining. AR transformers were around before LLMs and will be there after LLMs.

When I made this, the point was to show that you dont need pretraining (which is what makes an LLM) to perform well on complex tasks

And yes it is not a language model either. I did not train it on any language data. Only ARC puzzles

▲

soVeryTired 19 minutes ago | parent [-]

Out of interest, would you call BERT an LLM? It’s pre trained but not particularly large.

	▲	stymaar 14 minutes ago \| parent [-]
		AFAIK, the “large” qualifier came when transformers allowed to scale the size of language models compared to the recurrent models that where in fashion before. And although BERT isn't large by today's standard, it was large enough for the time.

▲

yorwba 13 minutes ago | parent | prev | next [-]

A LLM should at the very least be a language model, i.e. be able to take human-readable text as input or produce it as output. Transformers are used for plenty of tasks that don't involve language, for example object detection or blind source separation, where the models aren't called LMs; and on the other hand there are some LLM architectures that exclusively use linear attention variants and aren't really transformers anymore.

▲

soVeryTired 21 minutes ago | parent | prev [-]

It’s neither large nor language-based. ARC-AGI-1 is grid-based and nonverbal.

Use of a transformer is not necessary or sufficient to qualify as an LLM.

▲

f311a an hour ago | parent | prev [-]

The whole point of his model is to optimize for a very specific benchmark.

BUT, he does not use labels when training, so the model does not know the answers.

▲

embedding-shape an hour ago | parent [-]

> The whole point of his model is to optimize for a very specific benchmark.

But benchmaxxing is what we generally try to avoid for training, as there is no point really for it. We used to call it "overfitting", now you're saying this person does it intentionally? Why?

	▲	K0balt 40 minutes ago \| parent \| next [-]
		There are plenty of applications where a machine learning system needs to optimize for a very limited data set that is still intractable by linear logic systems of reasonable scale and complexity. It’s interesting, because he is using the legos of LLMs to build highly specialized machine learning systems, which is a very pragmatic approach. Obviously a lot of other ways to achieve similar goals, but it’s cool to see someone back porting the modern tools towards older style optimizations. Also, the complexity of the task he is using occupies an interesting middle ground of ultra high dimensionality (for a “simple” problem) while being limited in width to a narrow set of solves- a space where one would be tempted to imagine you would need a much more capable system.
	▲	f311a an hour ago \| parent \| prev [-]
		Why not? There is $700k reward for the next iteration of this benchmark https://www.kaggle.com/competitions/arc-prize-2026-arc-agi-2... I would not call this overfitting, it's finetuning for specific task where you have a benchmark.