Live data from Hacker News

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

simonwillison.net

331–340 of 415 posts

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

#333
post #115

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.)

To be a little more fair... that example is tidily slotted into the EXAMPLES section, under the heading "You can extract images from a video, or create a video from many images".

I don't think most people read the man pages top to bottom. And even if they did, then for as much grief as you're giving ffmpeg, llm has an even larger burden... no man page and the docs weigh in at over 8k lines.

I get the general point that ffmpeg is a powerful, complex tool... but this is a weird fight to pick.

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

#334
post #333
post #115

Earlier quoted context omitted.

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.)

To be a little more fair... that example is tidily slotted into the EXAMPLES section, under the heading "You can extract images from a video, or create a video from many images". I don't think most people read the man pages top to bottom. And even if they did, then for as much grief as you're giving ffmpeg, llm has an even larger burden... no man page and the docs weigh in at over 8k lines. I get the general point th…

I could not be more confident that "ffmpeg is difficult to figure out" is not a weird fight to pick. It's notorious!

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

#335

Earlier quoted context omitted.

Wasn't the bitter lesson about training on large amounts of data? The model that he's using was still trained on a massive corpus (22T tokens).

I think GP means that if you internalize the bitter lesson (more data more compute wins), you stop imagining how to squeeze SOTA minus 1 performance out of constrained compute environments.

This. When we ran out of speed on the CPU, we moved to the GPU. Same thing here. The more we work with (22T) models, quants, and decimating precision - the more we learn and find more novel ways to do things.

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

#336

I have an M4 Mac with 128GB RAM and I'm currently downloading GLM-4.5-Air-q5-hi-mlx via LM Studio (80GB) and will report back!

How is it going? Intrigued enough to possibly get an M4 Mac with 128GB RAM if it's worthwhile...

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

#337

(novice question) 64gb is pure RAM? I thought Apple Silicon was efficient at paging SSD as memory storage - how important is RAM if you've got a fast SSD?

While Apple Silicon's memory compression and SSD swapping are efficient, RAM access is still ~100x faster than SSD, so sufficient physical RAM remains crucial for memory-intensive workloads like running large LLMs.

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

#338
MLX does have decent/good software support among ML stacks. Targeting both iOS and mac is a big win in itself.

I wonder what's possible, what the software situation is today with the PC NPU's. AMD's XDNA has been around for a while, XDNA2 jumps from 10->40 TOps. AMD iGPU can access huge memory: is it similar here? The "AMDXDNA" driver merged in 6.14 last winter: where are we now?

But not seeing any evidence that there's popular support in any of the main frameworks. https://github.com/ggml-org/llama.cpp/issues/1499 https://github.com/ollama/ollama/issues/5186

Good news, AMD has an initial implementation of llama.cpp. I don't particularly know what it means, but the firt gen supports W4ABF16 quantization, newer chips support W8A16. https://github.com/ggml-org/llama.cpp/issues/14377 . I'm not sure what it's good for, but there is a Linux "xdna-driveR", https://github.com/amd/xdna-driver . IREE has an experimental backend: https://github.com/nod-ai/iree-amd-aie

There's a lot of other folks also starting on their NPU journeys. ARM's Ethos, and Rockchip's RKNN recently shipped Linux kernel drivers, but it feels like that's just a start? https://www.phoronix.com/news/Arm-Ethos-NPU-Accel-Driver https://www.phoronix.com/news/Rockchip-NPU-Driver-RKNN-2025

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

#339

I have an M4 Mac with 128GB RAM and I'm currently downloading GLM-4.5-Air-q5-hi-mlx via LM Studio (80GB) and will report back!

How is it going? Intrigued enough to possibly get an M4 Mac with 128GB RAM if it's worthwhile...

Apple is going to make so much money if they keep pushing on-device LLMs. It makes absolute sense to sell more macbook pros

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

#340
post #277
post #180

Earlier quoted context omitted.

[flagged]

Please don't cross into personal attack in HN comments. https://news.ycombinator.com/newsguidelines.html Edit: twice is already a pattern - https://news.ycombinator.com/item?id=44110785 . No more of this, please. Edit 2: I only just realized that you've been frequently posting abusive replies in a way that crosses into harangue if not harassment: https://news.ycombinator.com/item?id=44725284 (July 2025) https://news.…

[flagged]
Post reply on HN