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

401–410 of 415 posts

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

#401

Post by ben_w »

082349872349872 wrote: post #392
ben_w wrote: post #247

Earlier quoted context omitted.

I remember when I was a kid, people asking a teacher how to spell a word, and the answer was generally "look it up in a dictionary"… which you can only do if you already have shortlist of possible spellings. *nix man pages are the same: if you already know which tool can solve your problem, they're easy to use. But you have to already have a shortlist of tools that can solve your problem, before you even know which m…

man -k (or apropos)

`apropos` would itself be an example of a *nix tool that I didn't know existed and therefore wouldn't have known to find out more about.

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

#402

Post by aschobel »

simonw wrote: post #291
devmor wrote: post #274

Earlier quoted context omitted.

I'm not really sure what you're saying an LLM did in this case. Inspired a lost sense of curiosity?

My general point is that people say things like "yeah, but this one study showed that programmers over-estimate the productivity gain they get from LLMs so how can you really be sure?" Meanwhile I've spent the past two years constantly building and implementing things I never would have done because of the reduction in friction LLM assistance gives me. I wrote about this first two years ago - AI-enhanced development…

"You can just do things".

Agreed on all fronts. jq and AppleScript are a total syntax mystery to me, but now I use them all the times since claude code has figured them out.

It's so powerful knowing the shape of a solution on not having to care about the details.

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

#403

Post by yencabulator »

simonw wrote: post #297
shortrounddev2 wrote: post #294

Earlier quoted context omitted.

Serious question: if you have to read every line of code in order to validate it in production, why not just write every line of code instead?

Because it's much, much faster to review a hundred lines of code than it is to write a hundred lines of code. (I'm experienced at reading and reviewing code.)

This sounds like a recipe for destructive bugs and security vulnerabilities to slip into production.

Reviewing is really hard to do well. Like, on a psychological level. Your brain just starts nodding and humming along, pretending to understand. Humans have to consciously "perform review" to actually review. For example, https://en.wikipedia.org/wiki/Pointing_and_calling and checklists in aviation and health care, Tom Gilb's "Inspection" JPL-inspired spec review processes.

Even HN gets a steady drip of "look at my vibecoded project" -- "umm, you just leaked your API keys".

It's just that reviewing doesn't matter for a space invaders clone.

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

#404

Post by yencabulator »

giantrobot wrote: post #393
bsder wrote: post #307

Earlier quoted context omitted.

> However the solutions are absolutely useless for anyone else but the implementer. Disposable code is where AI shines . AI generating the boilerplate code for an obtuse build system? Yes, please. AI generating an animation? Ganbatte. (Look at how much work 3Blue1Brown had to put into that--if AI can help that kind of thing, it has my blessings). AI enabling someone who doesn't program to generate some prototype that…

> AI is also a problem because disposable code is what you would assign to junior programmers in order for them to learn. It's also giving PHBs the ability to hand ill-conceived ideas to a magic robot, receive "code" they can't understand, and throw it into production. All the while firing what real developers they had on staff.

I expect many of those companies to fail in the 3mo-2y timeline, so in many ways I welcome PHBs to embrace their full stupidity. Same for the people who funded them.

I do feel semi-sorry for anyone who paid for the services by those companies, though. Maybe something good will arise from that too, in the end; for example, it'd be nice if US society taught more critical reading skills to its members.

The interesting game for the non-PHBs among us is figuring out if/how we can use LLMs in less risky ways, and what all is possible there. For example, I'd love to see work put into LLMs helping with formal correctness of software; there's a hard backstop there where either the proof checks or it doesn't. Code changes needed to enable less-painful proofs would hopefully largely be refactorings, where reviews should be easier and it might even work out to fuzz test that the old and new implementations return matching output for same input. Or similarly, LLM-powered test coverage improver that only writes new tests (old school/branch-based/mutation-based, there's plenty of room there).

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

#405

Post by yencabulator »

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…

> 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.

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

#406

Post by simonw »

yencabulator wrote: post #403
simonw wrote: post #297

Earlier quoted context omitted.

Because it's much, much faster to review a hundred lines of code than it is to write a hundred lines of code. (I'm experienced at reading and reviewing code.)

This sounds like a recipe for destructive bugs and security vulnerabilities to slip into production. Reviewing is really hard to do well. Like, on a psychological level. Your brain just starts nodding and humming along, pretending to understand. Humans have to consciously "perform review" to actually review. For example, https://en.wikipedia.org/wiki/Pointing_and_calling and checklists in aviation and health care, To…

Reviewing isn't nearly as hard if you told the model exactly what to write already: https://simonwillison.net/2025/Mar/11/using-llms-for-code/#t...

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

#407

Post by h-bradio »

torarnv wrote: post #239
h-bradio wrote: post #171

Thanks so much for this! I updated LM Studio, and it picked up the mlx-lm update required. After a small tweak to tool-calling in the prompt, it works great with Zed!

Could you describe the tweak you did, and possibly the general setup you have with zed working with LM Studio? Do you use a custom system prompt? What context size do you use? Temperature? Thanks!

Here is how my prompt ended up! https://gist.github.com/hbradio/2f504c3fdb6f7113181b2d8c6862... I just asked an LLM to make it similar to a working Qwen prompt.

To make the LLMs able to use tools, I had to configure them in the Zed settings like this: https://gist.github.com/hbradio/fa4b456658a8d250e6ccc69ae9b3...

Also, I had to go into LM Studio and increase the max context size for each model I wanted to use in Zed. Otherwise it gives a parsing error on the response. I set it to the max allowable value.

I start LM Studio, start the LM Studio server, then go to Zeds AI config and tell it to connect to LM Studio. I put it in Agent mode, and it seems to work!

I don't know much about temperature, and I didn't use any other system prompt.

Good luck!

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

#408

Post by GardenLetter27 »

airspresso wrote: post #367
GardenLetter27 wrote: post #361

Crazy how Apple is still the only option for this consumer hardware.

Framework desktop with AMD Strix Halo [1] are getting there as a viable alternative. Offering up to 96 GB of unified RAM at the moment, so still a gap up to the beefiest Mac Studio alternatives though. [1]: https://frame.work/desktop

Surprisingly competitive pricing there though. It sucks that they're all priced around $3k in total though (with my Europoor VAT), but it's not as bad vs. Apple as I thought it would be.

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

#409

Post by eckelhesten »

Nesco wrote: post #256
NitpickLawyer wrote: post #6

> Two years ago when I first tried LLaMA I never dreamed that the same laptop I was using then would one day be able to run models with capabilities as strong as what I’m seeing from GLM 4.5 Air—and Mistral 3.2 Small, and Gemma 3, and Qwen 3, and a host of other high quality models that have emerged over the past six months. Yes, the open-models have surpassed my expectations in both quality and speed of release. For…

Zuck wouldn’t have leaked it on 4chan of all the places

It got leaked as a PR with an url to a magnet (torrent) afaik.

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

#410

Post by FeepingCreature »

phkahler wrote: post #95
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…

>> 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 st…

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.

Post reply on HN