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

201–210 of 415 posts

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

#201

Post by photon_lines »

simonw wrote: post #152
righthand wrote: post #146

Did you understand the implementation or just that it produced a result? I would hope an LLM could spit out a cobbled form of answer to a common interview question. Today a colleague presented data changes and used an LLM to build a display app for the JSON for presentation. Why did they not just pipe the JSON into our already working app that displays this data? People around me for the most part are using LLMs to e…

I scanned the code and understood what it was doing, but I didn't spend much time on it once I'd seen that it worked. If I'm writing code for production systems using LLMs I still review every single line - my personal rule is I need to be able to explain how it works to someone else before I'm willing to commit it. I wrote a whole lot more about my approach to using LLMs to help write "real" code here: https://simon…

This is why I love using the Deep-Seek chain of reason output ... I can actually go through and read what it's 'thinking' to validate whether it's basing its solution on valid facts / assumptions. Either way thanks for all of your valuable write-ups on these models I really appreciate them Simon!

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

#202

Post by pamelafox »

__mharrison__ wrote: post #90
pamelafox wrote: post #11

Alas, my 3 year old Mac has only 16 GB RAM, and can barely run a browser without running out of memory. It's a work-issued Mac, and we only get upgrades every 4/5 years. I must be content with 8B parameters models from Ollama (some of which are quite good, like llama3.1:8b).

Odd. My MBP has 16 GB and I routinely have 5 browsers windows open. Most of them have 5-20 tabs. I'm also routinely running vi vscode and editing videos with davinci resolve without issue. My only memory issue that I can remember is an OBS memory leak, otherwise these MBPs incredible hardware. I wish any other company could actually deliver a comparable machine.

I was exaggerating slightly - I think it's some combo of the apps I use: Edge, Teams, Discord, VS Code, Docker. When I get the RAM popup once a week, I typically have to close a few of those, whichever is using the most memory according to Activity Monitor. I've also got very little hard drive space on my machine, about 15 GB free, so that makes it harder for me to download the larger models. I keep trying to clear space, even using CleanMyMac, but I somehow keep filling it up.

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

#203

Post by sarchertech »

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…

> The source code for original Space Invaders from 1978 has never been published. The closest to that is disassembled ROMs.

Sure but that doesn’t impact the OPs point at all because there are numerous copies of reverse engineered source code available.

There are numerous copies of the reverse engineered source code already translated to JavaScript in your models training set.

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

#205

Post by weberer »

regularfry wrote: post #102
joelthelion wrote: post #70

Apart from using a Mac, what can you use for inference with reasonable performance? Is a Mac the only realistic option at the moment?

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.

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

#206

Post by qcnguy »

qingcharles wrote: post #175
kasey_junk wrote: post #167

Earlier quoted context omitted.

I’ve been mentally mapping tge models to the history of db. Most db in the early days you had to pay for. There are still for pay db that are just better than ones you don’t pay for. Some teams think that the cost is worth the improvements and there is a (tough) business there. Fortunes were made in the early days. But eventually open source models became good enough for many use cases and they have their own advanta…

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 same way. The big clouds offering proprietary fine tunes of models given away by AI labs using investor money?

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

#207

Post by ajcp »

th0ma5 wrote: post #180
simonw wrote: post #152

Earlier quoted context omitted.

I scanned the code and understood what it was doing, but I didn't spend much time on it once I'd seen that it worked. If I'm writing code for production systems using LLMs I still review every single line - my personal rule is I need to be able to explain how it works to someone else before I'm willing to commit it. I wrote a whole lot more about my approach to using LLMs to help write "real" code here: https://simon…

[flagged]

They said "production systems", not "critical production applications".

Also the 'if' doesn't negate anything as they say "I still", meaning the behavior is actively happening or ongoing; they don't use a hypothetical or conditional after "still", as in "I still would".

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

#209

Post by parsimo2010 »

maksimur wrote: post #197

A $xxxx 2.5 year old laptop, one that's probably much more powerful than an average laptop bought today and probably next year as well. I don't think it's a fair reference point.

The article is pretty good overall, but the title did irk me a little. I assumed when reading "2.5 year old" that it was fairly low-spec only to find out it was an M2 Macbook Pro with 64 GB of unified memory, so it can run models bigger than what an Nvidia 5090 can handle.

I suppose that it could be intended to be read as "my laptop is only 2.5 years old, and therefore fairly modern/powerful" but I doubt that was the intention.

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

#210

Post by svachalek »

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 performance/size ratio, generally if the model easily fits at q4 you're better off going to a higher parameter count than going for a larger quant, and vice versa)

Post reply on HN