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

351–360 of 415 posts

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

#351

Post by otabdeveloper4 »

simonw wrote: post #115
dingnuts wrote: post #111

Earlier quoted context omitted.

It is nice to use LLMs to generate ffmpeg commands, because those can be pretty tricky, but really, you wouldn't have just used the man page before? That explains a lot about Django that the author is allergic to man pages lol

I just took a look, and the man page DOES explain how to do that! ... on line 3,218: https://gist.github.com/simonw/6fc05ea7392c5fb8a5621d65e0ed0... (I am very confident I am not the only person who has been deterred by ffmpeg's legendarily complex command-line interface. I feel no shame about this at all.)

The correct solution here would have been to feed the man page to an LLM summarizer.

Alas instead of correct and easy solutions to problems we are focused on sci-fi robot assitant bullshit.

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

#352

Post by reverius42 »

diggan wrote: post #140
kelvinjps10 wrote: post #86

Earlier quoted context omitted.

coding? they are coding models? what specific tasks is one performing better than the other?

They may be, but there are lots of languages, lots of approaches, lots of methodologies and just a ton of different ways to "code", coding isn't one homogeneous activity that one model beats all the other models at. > what specific tasks is one performing better than the other? That's exactly why you create your own benchmark, so you can figure that out by just having a list of models, instead of testing each individ…

> coding isn't one homogeneous activity that one model beats all the other models at

If you can't even replace one coding model with another, it's hard to imagine you can replace human coders with coding models.

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

#353

Post by regularfry »

weberer wrote: post #205
regularfry wrote: post #102

Earlier quoted context omitted.

This one should just about fit on a box with an RTX 4090 and 64GB RAM (which is what I've got) at q4. Don't know what the performance will be yet. I'm hoping for an unsloth dynamic quant to get the most out of it.

Whats important is VRAM, not system RAM. The 4090 has 16gb of VRAM so you'll be limited to smaller models at decent speeds. Of course, you can run models from system memory, but your tokens/second will be orders of magnitude slower. ARM Macs are the exception since they have unified memory, allowing high bandwidth between the GPU and the system's RAM.

Yes and no. The 4090 has 24GB, not 16; but with a big MoE you're not getting everything in there anyway. In that case you really want all the weights in RAM so that swapping experts in isn't a load from disk.

It's not as good as unified RAM, but it's also workable.

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

#354

Post by simonh »

israrkhan wrote: post #346
RALaBarge wrote: post #330

Earlier quoted context omitted.

Ask it a series of the same questions after you train that you posed before training started. Is the quality lower?

That series of questions will measure only a particular area. I am concerned about destorying model capabilities in some other area that that I do not pay attention to, and have no way of knowing.

Isn’t that a general problem with LLMs? The only way to know how good it is at something is to test it.

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

#355

Post by pyman »

simonw wrote: post #280

There's a new model from Qwen today - Qwen3-30B-A3B-Instruct-2507 - that also runs comfortably on my Mac (using about 30GB of RAM with an 8bit quantization). I tried the "Write an HTML and JavaScript page implementing space invaders" prompt against it and didn't quite get a working game with a single shot, but it was still an interesting result: https://simonwillison.net/2025/Jul/29/qwen3-30b-a3b-instruct...

I was talking about the new open models with a group of people yesterday, and saying how good they're getting. The big question is:

Can any company now compete with the big players? Or even more interesting, like you showed in your research, are proprietary models becoming less relevant now that anyone can run these models locally?

This trend of better open models that run locally is really picking up. Do you think we'll get to a point where we won't need to buy AI tokens anymore?

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

#356

Post by cztomsik »

Uehreka wrote: post #136
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...

> 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 t…

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)

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

#357

Post by rafaelmn »

skeezyboy wrote: post #168
rafaelmn wrote: post #88

Earlier quoted context omitted.

What about power used and support hardware ? Also card going down means you are down until you get warranty service.

why are you doing anything locally then?

Latency and tooling support ? UX of cloud based LLM vs local is much better for the cloud option - not so much for dev tooling.

I tried using remote workstations - I am not a fan of lugging a beefy client machine to do my work - would much rather use something thats super light and power efficient.

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

#358

Post by Mashimo »

LandR wrote: post #225
tptacek wrote: post #100

Earlier quoted context omitted.

OK, go write Space Invaders by hand.

I'd hope most professional software engineers could do this in an afternoon or so?

Depends on the rules. Can I look up other space invaders games on github first? Can I use a game framework?

Just JS / HTML docs I probably could not.

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

#359

Post by pyman »

simonw wrote: post #345
ygritte wrote: post #344

Can you host that model locally with ollama?

I haven't seen a GGUF for it yet, I imagine one will show up on Hugging Face soon which will probably work with Ollama.

Do you think local LLMs combined with P2P networks could become a thing? Imagine people adding datasets to an open model, the same way they add blocks to a blockchain, which is around 500GB in size.

It could help decentralise power and reduce our dependency on the big players.

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

#360

Post by numpad0 »

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.

humans also eat
Post reply on HN