Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)

simonwillison.net

Post reply on HN
Print view View original

61–70 of 415 posts

Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)

#61

Post by bayindirh »

FeepingCreature wrote: post #55
bayindirh wrote: post #42

Earlier quoted context omitted.

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...

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 "exper…

Humans can observe ants and invent any colony optimization. AIs can’t.

Humans can explore what they don’t know. AIs can’t.

Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)

#62

Post by jayd16 »

NitpickLawyer wrote: post #20
AlexeyBrin wrote: post #5

Most likely its training data included countless Space Invaders in various programming languages.

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-tra…

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.

Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)

#63

Post by tossandthrow »

alankarmisra wrote: post #59

I see the value in showcasing that LLMs can run locally on laptops — it’s an important milestone, especially given how difficult that was before smaller models became viable. That said, for something like this, I’d probably get more out of simply finding an existing implementation on github or the like and downloading that. When it comes to specialized and narrow domains like Space Invaders, the training set is likel…

Interesting, I can not produce these warnings in ChatGPT - though this is something that really interests me, as it represents immense political power to be able ti interject such warnings (explicitly, or implicitly by slight reformulations)

Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)

#64

Post by satvikpendem »

bayindirh wrote: post #42
quantumHazer wrote: post #13

Earlier quoted context omitted.

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

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...

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.

Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)

#65

Post by turnsout »

jphoward wrote: post #19
OJFord wrote: post #12

Earlier quoted context omitted.

I think the point is just that it doesn't require absolute cutting edge nor server hardware.

No but 64 GB of unified memory provides almost as much GPU RAM capacity as two RTX 5090s (only less due to the unified nature) - top of the range GPUs - so it's a truly exceptional laptop in this regard.

Except that it is not exceptional at all; it's an older-generation MacBook Pro with 64GB of RAM. There's nothing particularly unusual about it.

Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)

#68

Post by falcor84 »

bayindirh wrote: post #61
FeepingCreature wrote: post #55

Earlier quoted context omitted.

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 "exper…

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.

Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)

#69

Post by jan_Sate »

NitpickLawyer wrote: post #20
AlexeyBrin wrote: post #5

Most likely its training data included countless Space Invaders in various programming languages.

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-tra…

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.

Post reply on HN