I get the impression one of the most effective tricks is to load your training set up with as much code as possible that has comprehensive automated tests that pass already.
I've been profoundly humbled by the the experience, but then it occurred to me that what I thought to be an unique problem has been solved by quite a few people before and the model had plenty of references to pull from.
For a counterexample, working on any part of a codebase that's 100% application specific business logic, with our custom abstractions, the AI is usually so lost that it's basically not even worth using it, as the chances of writing correct and usable code is next to zero.
No. It explains why models seem better at code in given situations. When your prompt mapped to diffs in the training data that are useful to you they seem great.
I've tried things like searching all of the public code on GitHub for every possible keyword relevant to my problem.
... or I'm writing code against libraries which didn't exist when the models were trained.
The idea that models can only write code if they've seen code that does the exact same thing in the past is uninformed in my opinion.
This is a conceited interpretation of what I said.
I quoted the paper "Evolution through Large Models" written in collaboration between OpenAI and Anthropic researchers
"In other words, the model learns to predict plausible changes to code from examples of changes made to code by human programmers."
https://arxiv.org/pdf/2206.08896
> The idea that models can only write code if they've seen code that does the exact same thing in the past
How do you get "code that does the exact same thing" from "predicting plausible changes?"
Are Gemini and DeepSeek and Llama and other strong coding models using the same ideas?
Llama and DeepSeek are at least slightly more open about their training processes so there might be clues in their papers (that's a lot of stuff to crunch through though).
This seems to be very hard for people to accept, per the other comments here.
Until recently I was willing to accept an argument that perhaps LLMs had mostly learned the patterns; e.g. to maybe believe 'well there aren't that many really different leetcode questions'.
But with recent models (eg sonnet-3.7-thinking) they are operating well on such large and novel chunks of code that the idea they've seen everything in the training set, or even, like, a close structural match, is becoming ridiculous.
I am sure that the functionalities implemented are novel but do you really think the training data cannot possibly have had the patterns being used to deliver these features, really? How is it that in the past few months or years people suddenly found the opportunity and motivation to write code that cannot possibly be in any way shape or form represented by patterns in the diffs that have been pushed in the past 30 years?
I'm not claiming LLMs can invent new computer science. I'm saying it's not accurate to say "they can only produce code that's almost identical to what's in their training data".
Again, you're misinterpreting in a way that seems like you are reacting to the perception that someone attacked some of your core beliefs rather than considering what I am saying and conversing about that.
I never even used the words "exact same thing" or "almost identical". Not even synonyms. I just said overfitting and quoted from an OpenAI/Anthropic paper that said "predict plausible changes to code from examples of changes"
Think about that. Don't react, think. Why do you equate overfitting and plausibility prediction with "exact" and "identical". It very obviously is not what I said.
What I am getting at is that a cannon will kill the mosquito. But drawing a fly swatter in the cannonball and saying the plastic ones are obsolete now would be in bad faith. No need to say to someone pointing that out that they are claiming that the cannon can only fire on mosquitoes that have been swatted before.
Reading back, you said:
> I often see people wondering if the some coding task is performed well or not because of availability of code examples in the training data. It's way worse than that. It's overfitting to diffs it was trained on.
I'll be honest: I don't understand what you mean by "overfitting to diffs it was trained on" there.
Maybe I don't understand what "overfitting" means in this context?
(I'm afraid I didn't understand your cannon / fly swatter analogy either.)
That is the premise of LLM-as-AI. By training these models on enough data, knowledge of the world is purported as having been captured, creating something useful that can be leveraged to process new input and get a prediction of the trajectory of the system in some phase space.
But this, I argue, is not the case. The models merely overfit to the training data. Hence the variable results perceived by people. When their intentions and prompt fit to the data in the training, the model appears to give good output. But the situation and prompt do not, the models do no "reason" about it and "infer" anything. It fails. It gives you gibberish or go in circles, or worse if there is some "agentic" arrangement if fails to terminate and burns tokens until you intervene.
It's overkill. And I am pointing out it is overkill. It's not a clever system for creating code for any given situation. It overfits to training data set. And your response is to claim that my argument is something else, not that it's overkill but that it can only kill dead things. I never said that. I see it's more than capable of spitting out useful code even if that exact same code is not in the training dataset. But it is just automating the process of going through google, docs and stack overflow and assembling something for you. You might be good at searching and lucky and it is just what you need. You might not be so used to using the right keywords or just be using some uncommon language, or in a domain that happens to not be well represented and then it feels less useful. But instead of just coming up short as search, the model overkills and wastes your time and god knows how much subsidized energy and compute. Lucky you if you're not burning tokens on some agentic monstosity.
(I'm not personally interested in the whole AGI thing.)
This whole exchange was you having knee-jerk reactions to things you imagined I said. It has been incredibly frustrating. And at the end you shrug and say "eh it's useful to me"??
I am talking about this because of deceitfulness, resource efficiency, societal implications of technology.
In my own writing I don't even use the term "AI" very often because its meaning is so vague.
You're right to call me out on this: I did, in this earlier comment - https://news.ycombinator.com/item?id=43644662#43647037 - commit the sin of responding to something you hadn't actually said.
(Worse than that, I said "... is uninformed in my opinion" which was rude because I was saying that about a strawman argument.)
I did that thing where I saw an excuse to bang on one of my pet peeves (people saying "LLMs can't create new code if it's not already in their training data") and jumped at the opportunity.
I've tried to continue the rest of the conversation in good faith though. I'm sorry if it didn't come across that way.
Simon, intelligence exists (and unintelligence exists). When you write «I'm not claiming LLMs can invent new computer science», you imply intelligence exists.
We can implement it. And it is somehow urgent, because intelligence is very desirable wealth - there is definite scarcity. It is even more urgent after the recent hype has made some people perversely confused about the idea of intelligence.
We can and must go well beyond the current state.
Such failure could happen if the models were overfit, or for other reasons. I don't think 'overfit', which is pretty well defined, is exactly the word you mean to use here.
However, I respectfully disagree with your claim. I think they are generalising well beyond the training dataset (though not as far beyond as say a good programmer would - at least not yet). I further think they are learning semantically.
Can't prove it in a comment except to say that there's simply no way they'd be able to successfully manipulate such large pieces of code, using English language instructions, it they weren't great at generalisation and ok at understanding semantics.
But this is the crux of the disagreement. I think the models overfit to the training data hence the fluctuating behavior. And you think they show generalization and semantic understanding. Which yeah they apparently do. But the failure modes in my opinion show that they don't and would be explained by overfitting.