Most likely its training data included countless Space Invaders in various programming languages.
back
6 comments
The real test is if you can have it tweak things. Have the ship shoot down. Have the space invaders come from the left and right. Add two player simultaneous mode with two ships.
It can usually tweak things, if given specific instruction, but it doesn't know when to refactor (and can't reliably preserve functionality when it does), so the program gets further and further away from something sensible until it can't make edits any more.
For serious projects you can address that by writing (or having it write) unit tests along the way, that way it can run in a loop and avoid breaking existing functionality when it adds new changes.
Okay ask it to write unit tests for space invaders next time :)
and probably some synthetic data are generated copy of the games already on the dataset?
i have this feeling with LLM's generated react frontend, they all look the same
To be fair, the human-generated user interfaces all look the same too.
Have you used the internet? thats how the internet looks, their all fuckin react and the same layouts and styles 90% shadcn lol
most human generated methods look the same. in fact, in SWE, we reward people for generating code that look & feel the same, they call it "work as a team".
Last time somebody asked for a "premium camera app for iOS", and the model (re)generated Halide.
Models don't emit something they don't know. They remix and rewrite what they know. There's no invention, just recall...
> Models don't emit something they don't know. They remix and rewrite what they know. There's no invention, just recall...
People really need to stop saying this. I get that it was the Smart Guy Thing To Say in 2023, but by this point it’s pretty clear that that it’s not true in any way that matters for most practical purposes.
Coding LLMs have clearly been trained on conversations where a piece of code is shown, a transformation is requested (rewrite this from Python to Go), and then the transformed code is shown. It’s not that they’re just learning codebases, they’re learning what working with code looks like.
Thus you can ask an LLM to refactor a program in a language it has never seen, and it will “know” what refactoring means, because it has seen it done many times, and it will stand a good chance of doing the right thing.
That’s why they’re useful. They’re doing something way more sophisticated than just “recombining codebases from their training data”, and anyone chirping 2023 sound bites is going to miss that.
I don't know, I have mixed-bag experiences and it's not really improving. It greatly varies depending on the programming language and the kind of problem which I'm trying to solve.
The tasks where it works great are things I'd expect to be part of dataset (github, blog posts), or they are "classic" LM tasks (understand + copy-paste/patch). The actual intelligence, in my opinion, is still very limited. So while it's true it's not "just recall" it still might be "mostly recall".
BTW: Copy-paste is something which works great in any attention-based model. On the other hand, models like RWKV usually fail and are not suited for this IMHO (but I think they have much better potential for the AGI)
> It’s not that they’re just learning codebases, they’re learning what working with code looks like.
Working in any not-in-training-set environment very quickly shows the shortcomings of this belief.
For example, Cloudflare Workers is V8 but it sure ain't Node, and the local sqlite in a Durable Object has a sync API with very different guarantees than a typical client-server SQL setup.
Even in a more standard setting, it's really hard to even get an LLM to use the current-stable APIs when its training data contains now-deprecated examples. Your local rules, llms.txt mentions, corrections etc slip out of the context pretty fast and it goes back to trained data.
The LLM can perhaps "read any code" but it really really prefers writing only code that was in its training set.
True where trivial; where nontrivial, false.
Trivially, humans don't emit something they don't know either. You don't spontaneously figure out Javascript from first principles, you put together your existing knowledge into new shapes.
Nontrivially, LLMs can absolutely produce code for entirely new requirements. I've seen them do it many times. Will it be put together from smaller fragments? Yes, this is called "experience" or if the fragments are small enough, "understanding".
>> Nontrivially, LLMs can absolutely produce code for entirely new requirements. I've seen them do it many times.
I think most people writing software today are reinventing a wheel, even in corporate environments for internal tools. Everyone wants their own tweak or thinks their idea is unique and nobody wants to share code publicly, so everyone pays programmers to develop buggy bespoke custom versions of the same stuff that's been done 100 times before.
I guess what I'm saying is that your requirements are probably not new, and to the extent they are yes an LLM can fill in the blanks due to its fluency in languages.
Nothing is truly and completely new. I'm not formulating my requirements in an extinct language. My point is "filling in the blanks" and "do new things" are a spectrum.
LLMs have their limits, but they really can understand and productively contribute to programs that achieve a purpose that no program on the internet has done yet. What they are doing is not interpolation at the highest level. It may be interpolation/extrapolation at a lower level, but this goes for any skill learnt by anyone ever.
Humans can observe ants and invent any colony optimization. AIs can’t.
Humans can explore what they don’t know. AIs can’t.
What makes you categorically say that "AIs can't"?
Based on my experience with present day AIs, I personally wouldn't be surprised at all that if you showed Gemini 2.5 Pro a video of an insect colony and asked it "Take a look at the way they organize and see if that gives you inspiration for an optimization algorithm", it will spit something interesting out.
What makes you categorically say that "humans can"?
I couldn't do that with an ant colony. I would have to train on ant research first.
(Oh, and AIs can absolutely explore what they don't know. Watch a Claude Code instance look at a new repository. Exploration is a convergent skill in long-horizon RL.)
> Humans can observe ants and invent any colony optimization. AIs can’t.
Surely this is exactly what current AI do? Observe stuff and apply that observation? Isn't this the exact criticism, that they aren't inventing ant colonies from first principles without ever seeing one?
> Humans can explore what they don’t know. AIs can’t.
We only learned to decode Egyptian hieroglyphs because of the Rosetta Stone. There's no translation for North Sentinelese, the Voynich manuscript, or Linear A.
We're not magic.
That's what benchmarks like ARC-AGI are designed to test. The models are getting better at it, and you aren't.
Nothing ultimately matters in this business except the first couple of time derivatives.
humans also eat
This doesn't make sense thermodynamically because models are far smaller than the training data they purport to hold and recall, so there must be some level of "understanding" going on. Whether that's the same as human understanding is a different matter.
It’s a lossy text compression technique. It’s clever applied statistics. Basically an advanced association rules algorithm which has been around for decades but modified to consider order and relative positions.
There is no understanding, regardless of the wants of all the capital investors in this domain.
I don't care if it can "understand" anything, as long as I can use it to achieve useful things.
It’s a lossy text compression technique.
That is a much, much bigger deal than you make it sound like.
Compression may, in fact, be all we need. For that matter, it may be all there is.
> They remix and rewrite what they know. There's no invention, just recall...
If they only recalled they wouldn’t “hallucinate”. What’s a lie if not an invention? So clearly they can come up with data that they weren’t trained on, for better or worse.
Because internally, there isn't a difference between correctly "recalled" token and incorrectly (hallucinated).
Depends on the training? If there was eg RLHF then those connections are stronger and more likely; that's a difference (but not a category difference).
This comment is ~3 years late. Every model since gpt3 has had the entirety of available code in their training data. That's not a gotcha anymore.
We went from chatgpt's "oh, look, it looks like python code but everything is wrong" to "here's a full stack boilerplate app that does what you asked and works in 0-shot" inside 2 years. That's the kicker. And the sauce isn't just in the training set, models now do post-training and RL and a bunch of other stuff to get to where we are. Not to mention the insane abilities with extended context (first models were 2/4k max), agentic stuff, and so on.
These kinds of comments are really missing the point.
I've had little success with Agentic coding, and what success I have had has been paired with hours of frustration, where I'd have been better off doing it myself for anything but the most basic tasks.
Even then, when you start to build up complexity within a codebase - the results have often been worse than "I'll start generating it all from scratch again, and include this as an addition to the initial longtail specification prompt as well", and even then... it's been a crapshoot.
I _want_ to like it. The times where it initially "just worked" felt magical and inspired me with the possibilities. That's what prompted me to get more engaged and use it more. The reality of doing so is just frustrating and wishing things _actually worked_ anywhere close to expectations.
Bingo, it's magical but the learning curve is very very steep. The METR study on open-source productivity alluded to this a bit.
I am definitely at a point where I am more productive with it, but it took a bunch of effort.
Apologies if I was unclear.
The more I've used it, the more I've disliked how poor the results it's produced, and the more I've realised I would have been better served by doing it myself and following a methodical path for things that I didn't have experience with.
It's easier to step through a problem as I'm learning and making small changes than an LLM going "It's done, and production ready!" where it just straight up doesn't work for 101 different tiny reasons.
The subjects in the study you are referencing also believed that they were more productive with it. What metrics do you have to convince yourself you aren't under the same illusionary bias they were?
Not exactly. The real utility value of LLM for programming is to come up with something new. For Space Invaders, instead of using LLM for that, I might as well just manually search for the code online and use that.
To show that LLM actually can provide value for one-shot programming, you need to find a problem that there's no fully working sample code available online. I'm not trying to say that LLM couldn't to that. But just because LLM can come up with a perfectly-working Space Invaders doesn't mean that it could do that.
> The real utility value of LLM for programming is to come up with something new.
That's the goal for these projects anyways. I don't know that its true or feasible. I find the RAG models much more interesting myself, I see the technology as having far more value in search than generation.
Rather than write some markov-chain reminiscent frankenstein function when I ask it how to solve a problem, I would like to see it direct me to the original sources it would use to build those tokens, so that I can see their implementations in context and use my judgement.
"I would like to see it direct me to the original sources it would use to build those tokens"
Sadly that's not feasible with transformer-based LLMs: those original sources are long gone by the time you actually get to use the model, scrambled a billion times into a trained set of weights.
One thing that helped me understand this is understanding that every single token output by an LLM is the result of a calculation that considers all X billion parameters that are baked into that model (or a subset of that in the case of MoE models, but it's still billions of floating point calculations for every token.)
You can get an imitation of that if you tell the model "use your search tool and find example code for this problem and build new code based on that", but that's a pretty unconventional way to use a model. A key component of the value of these things is that they can spit out completely new code based on the statistical patterns they learned through training.
I have a friend who has been doing just that... usually with his company he manages a handful of projects where a bulk of the development is outsourced overseas. This past year, he's outpaced the 6 devs he's had working on misc projects just with his own efforts and AI. Most of this being a relatively unique combination of UX with features that are less common.
He's using AI with note taking apps for meetings to enhance notes and flush out technology ideas at a higher level, then refining those ideas into working experiments.
It's actually impressive to see. My personal experience has been far more disappointing to say the least. I can't speak to the code quality, consistency or even structure in terms of most people being able to maintain such applications though. I've asked to shadow him through a few of his vibe coding sessions to see his workflow. It feels rather alien to me, again my experience is much more disappointing in having to correct AI errors.
Is this the same person who posted about launching 17 "products" in one year a few days ago on HN? :)
You are reading too much into my comment. My point was that the test (a Space Invaders clone) used to asses the model is irrelevant for some time now. I could have gotten a similar result with Mistral Small a few months ago.
It's amazing that none of you even try to falsify you claims anymore. You can literally just put some of the code in a search engine and find the prior art example:
https://www.web-leb.com/en/code/2108
Your "AI tools" are just "copyright whitewashing machines."
These kinds of comments are really ignoring reality.
I don't think they are missing the point, because they're pointing out that the tools are still the most useful for patterns that are extremely widely known and repeated. I use Gemini 2.5 Pro every day for coding, and even that one still falls over on tasks that aren't well known to it (which is why I break the problem down into small parts that I know it'll be able to handle properly).
It's kind of funny, because sometimes these tools are magical and incredible, and sometimes they are extremely stupid in obvious ways.
Yes, these are impressive, and especially so for local models that you can run yourself, but there is a gap between "absolutely magical" and "pretty cool, but needs heavy guiding" depending on how heavily the ground you're treading has been walked upon.
For a heavily explored space, it's like being impressed that you're 2.5 year old M2 with 64 GB RAM can extract some source code from a zip file. It's worth being impressed and excited about the space and the pace of improvement, but it's also worth stepping back and thinking rationally about the specific benchmark at hand.
> because they're pointing out that the tools are still the most useful for patterns that are extremely widely known and repeated
I agree with you, but your take is much more nuanced than what the GP comment said! These models don't simply regurgitate the training set. That was my point with gpt3. The models have advanced from that, and can now "generalise" over the context in ways they could not do ~3 years ago. We are now at a point where you can write a detailed spec (10-20k tokens) for an unseen scripting language, and have SotA models a) write a parser and b) start writing scripts for you in that language, even though it never saw that particular scripting language anywhere in its training set. Try it. You'll be surprised.
I think you're missing the point.
Showing off moderately complicated results that are actually not indicative of performance because they are sniped by the training data turns this from a cool demo to a parlor trick.
Stating that, aha, jokes on you, that's the status quo, is an even bigger indictment.
> These kinds of comments are really missing the point.
I disagree. In my experience, asking coding tools to produce something similar to all of the tutorials and example code out there works amazingly well.
Asking them to produce novel output that doesn’t match the training set produces very different results.
When I tried multiple coding agents for a somewhat unique task recently they all struggled, continuously trying to pull the solution back to the standard examples. It felt like an endless loop of the models grinding through a solution and then spitting out something that matched common examples, after which I had to remind them of the unique properties of the task and they started all over again, eventually arriving back in the same spot.
It shows the reality of working with LLMs and it’s an important consideration.
I find the visual similarity to breakout kind of interesting.
That sounds so dismissive.
I was not able to just download a 8-16GB File and then it would be able to generate A LOT of different tools, games etc. for me in multiply programming languages while in parallel ELI5 me research papers, generate svgs and a lot lot lot more.
But hey.
Most likely this comment included countless similar comments in its training data, likely all synthetic without any actual tether to real analysis.