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

341–350 of 415 posts

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

#341

Post by reissbaker »

delijati wrote: post #319
reissbaker wrote: post #270

Earlier quoted context omitted.

For self-hosting, there are a few companies that offer per-token pricing for LoRA finetunes (LoRAs are basically efficient-to-train, efficient-to-host finetunes) of certain base models: - (shameless plug) My company, Synthetic, supports LoRAs for Llama 3.1 8b and 70b: https://synthetic.new All you need to do is give us the Hugging Face repo and we take care of the rest. If you want other people to try your model, we…

Do you maybe know if there is a company in the EU that hosts models (DeepSeek, Qwen3, Kimi)?

Most inference companies (Synthetic included) host in a mix of the U.S. and EU — I don't know of any that promise EU-only hosting, though. Even Mistral doesn't promise EU-only AFAIK, despite being a French company. I think at that point you're probably looking at on-prem hosting, or buying a maxed-out Mac Studio and running the big models quantized to Q4 (although even that couldn't run Kimi: you might be able to get it working over ethernet with two Mac Studios, but the tokens/sec will be pretty rough).

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

#342

Post by wizzwizz4 »

stelonix wrote: post #329
wizzwizz4 wrote: post #302

Earlier quoted context omitted.

DuckDuckGo search results for "cli, extract frame 13s into video" (no quotes): • https://stackoverflow.com/questions/10957412/fastest-way-to-... • https://superuser.com/questions/984850/linux-how-to-extract-... • https://www.aleksandrhovhannisyan.com/notes/video-cli-cheat-... • https://www.baeldung.com/linux/ffmpeg-extract-video-frames • https://ottverse.com/extract-frames-using-ffmpeg-a-comprehen... Search engines h…

Yet the interface is fundamentally different, the output feels much more like bro pages[0] and it's within a click of clipboarding, one CTRL V away from extracting the 13th second screenshot. I've been using Google the past 24 years and my google-fu has always left people amazed; yet I can no longer bother to go through Stack Exchange's results when an LLM not only spits it out so nicely, but also does the equivalent…

DuckDuckGo insists on shoving "AI Assist" entries in its results, so I have a reasonable idea of how often LLMs are completely wrong even given search results. The answer's still "more than one time in five".

I did not suggest using Google Search (the company's on record as deliberately making Google Search worse), but there are other search engines. My preferred search engines don't do the fancy "interpret natural language queries" pre-processing, because I'm quite good at doing that in my head and often want to research niche stuff, but there are many still-decent search engines that do, and don't have ads in the results.

Heck, you can even pay for a good search engine! And you can have it redirect you to the relevant section of the top search result automatically: Google used to call this "I'm feeling lucky!" (although it was before URI text fragments, so it would just send you to the top of the page). All the properties you're after, much more cheaply, and you keep the information about provenance, and your answer is more-reliably accurate.

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

#343

Post by sagarm »

simonw wrote: post #25
neutronicus wrote: post #22

If I understand correctly, the author is managing to run this model on a laptop with 64GB of RAM? So a home workstation with 64GB+ of RAM could get similar results?

Only if that RAM is available to a GPU, or you're willing to tolerate extremely slow responses. The neat thing about Apple Silicon is the system RAM is available to the GPU. On most other systems you would need ~48GB of VRAM.

LLM evaluation on GPU and CPU is memory bandwidth constrained. The highest-end Apple machines are good for this because they have ~500GBps high memory bandwidth and up to ~128GB, not just because they can share that memory with the GPU (which any iGPU does). Most consumer machines are limited to 2xDDR5 channels (~50GBps).

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

#346

Post by israrkhan »

RALaBarge wrote: post #330
israrkhan wrote: post #323

Earlier quoted context omitted.

do you have a suggestion or a way to measure if model capabilities are getting destroyed? how do one measure it objectively?

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.

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

#347

Post by tw1984 »

quantumHazer wrote: post #13
AlexeyBrin wrote: post #5

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

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

most human generated methods look the same. in fact, in SWE, we reward people for generating code that look & feel the same, they call it "work as a team".

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

#348

Post by otabdeveloper4 »

genewitch wrote: post #96
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…

I'll bite. How do i train/make and/or use LoRA, or, separately, how do i fine-tune? I've been asking this for months, and no one has a decent answer. websearch on my end is seo/geo-spam, with no real instructions. I know how to make an SD LoRA, and use it. I've known how to do that for 2 years. So what's the big secret about LLM LoRA?

> So what's the big secret about LLM LoRA?

No clear use case for LLMs yet. ("Spicy" aka pornography finetunes are the only ones with broad adoption, but we don't talk about that in polite society here.)

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

#349

Post by otabdeveloper4 »

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.)

Absolutely false for anything but the most braindead corporate CRUD code.

We hate reading code and will avoid the hassle every time, but that doesn't mean it is easy.

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

#350

Post by otabdeveloper4 »

bnchrch wrote: post #198
th0ma5 wrote: post #180

Earlier quoted context omitted.

[flagged]

You do realize your talking to the creator of Django, Datassette, and Lanyrd right?

Offtopic, but Django is really bad and a huge pile of code smell. (Not a Django programmer. I manage them and can compare Django-infected projects to normal projects.)
Post reply on HN