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

231–240 of 415 posts

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

#231

Post by sharkjacobs »

falcor84 wrote: post #74
stpedgwdgfhgdd wrote: post #44

Aside that space invaders from scratch is not representative for real engineering, it will be interesting to see what the business model for Anthropic will be if I can run a solid code generation model on my local machine (no usage tier per hour or week), let’s say, one year from now. At $200 per month for 2 years I can buy a decent Mx with 64GB (or perhaps even 128GB taking residual value into account)

How come it's "not representative for real engineering"? Other than copy-pasting existing code (which is not what an LLM does), I don't see how you can create a space invaders game without applying "engineering".

Making a space invaders game is not representative of normal engineering because you're reproducing an existing game with well known specs and requirements. There are probably hundreds of thousands of words describing and discussing Space Invaders in GLM-4.5's training data

It's like using an LLM to implement a red black tree. Red black trees are in the training data, so you don't need to explain or describe what you mean beyond naming it.

"Real engineering" with LLMs usually requires a bunch of up front work creating specs and outlines and unit tests. "Context engineering"

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

#232

Post by quesera »

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.)

Ffmpeg is genuinely complicated! And the CLI is convoluted (in justifiable, and unfortunate ways).

But if you approach ffmpeg from the perspective of "I know this is possible", you are always correct, and can almost always reach the "how" in a handful of minutes.

Whether that's worth it or not, will vary. :)

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

#233

Post by nottorp »

tracker1 wrote: post #135
jan_Sate wrote: post #69

Earlier quoted context omitted.

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.…

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 enha…

Is this the same person who posted about launching 17 "products" in one year a few days ago on HN? :)

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

#234

Post by sejje »

skeezyboy wrote: post #199
svachalek wrote: post #189

Earlier quoted context omitted.

It's more a question of, how long do you want it to take to create a video locally?

nah, i definitely want to know what i asked

His answer implies you can run them locally now, just not in a useful timeframe.

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

#235

Post by nottorp »

simonw wrote: post #141
hbn wrote: post #133

Earlier quoted context omitted.

The prompt was > Write an HTML and JavaScript page implementing space invaders It may not be "copy pasting" but it's generating output as best it can be recreated from its training on looking at Space Invaders source code. The engineers at Taito that originally developed Space Invaders were not told "make Space Invaders" and then did their best to recall all the source code they've looked at in their life to re-type…

The source code for original Space Invaders from 1978 has never been published. The closest to that is disassembled ROMs. I used that prompt because it's the shortest possible prompt that tells the model to build a game with a specific set of features. If I wanted to build a custom game I would have had to write a prompt that was many paragraphs longer than that. The aim of this piece isn't "OMG looks LLMs can build…

> What's interesting is that my laptop can run a model that is capable of that now.

I'm afraid no one cared much about your point :)

You'll only get "OMG look how good LLMs are they'll get us all fired!" comments and "LLMs suck" comments.

This is how it goes with religion...

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

#236

Post by nottorp »

svachalek wrote: post #210
pulkitsh1234 wrote: post #8

Is there any website to see the minimum/recommended hardware required for running local LLMs? Much like 'system requirements' mentioned for games.

In addition to the tools other people responded with, a good rule of thumb is that most local models work best* at q4 quants, meaning the memory for the model is a little over half the number of parameters, e.g. a 14b model may be 8gb. Add some more for context and maybe you want 10gb VRAM for a 14gb model. That will at least put you in the right ballpark for what models to consider for your hardware. (*best performa…

> maybe you want 10gb VRAM for a 14gb model

... or if you have Apple hardware with their unified memory, whatever the assholes soldered in is your limit.

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

#237

Post by sejje »

ducktective wrote: post #216
simonw wrote: post #187

Earlier quoted context omitted.

That's why the IMO results were so notable: that was one of those moments where new models were demonstrated doing something that they had previously been unable to do.

I can't fathom why more people aren't talking about the IMO story. Apparently the model they used is not just an LLM but some RL are involved too. If a model wins gold at IMO, is it still merely a "statistical parrot"?

Stochastic parrot is the term.

I don't think it's ever been accurate.

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

#238

Post by qingcharles »

qcnguy wrote: post #206
qingcharles wrote: post #175

Earlier quoted context omitted.

You make a good point -- a majority of applications are now using open source or free versions[1] of DBs. My only feedback is: are these the same animal? Can we compare an O/S DB vs. paid/closed DB to me running an LLM locally? The biggest issue right now with LLMs is simply the cost of the hardware to run one locally, not the quality of the actual software (the model). [1] e.g. SQL Server Express is good enough for…

A majority of apps nowadays are using proprietary forks of open source DBs running in the cloud, where their feature set is (slightly) rounded out and smoothed off by the cloud vendors. Not that many projects are doing fully self-hosted RDBMS at this point. So ultimately proprietary databases still win out, they just (ab)use the Postgresql trademark to make people think they're using open source. LLMs might go the sa…

That's definitely true. I could see more of the running open source models on other people's hardware model.

I dislike running local LLMs right now because I find the software kinda janky still, you often have to tweak settings, find the right model files. Basically have a bunch of domain knowledge I don't have space for in my head. On top of maintaining a high-spec piece of hardware and paying for the power costs.

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

#239

Post by torarnv »

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!
Post reply on HN