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

191–200 of 415 posts

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

#191

Post by croes »

gchamonlive wrote: post #7
croes wrote: post #2

I bet the training data included enough space invader cloned in JS

Which would make this disappointing if it was only good at cloning space invaders. If it can reproduce all the clone it has ever seen it would still be an impressive feat. I just think we should stop to appreciate exactly how awesome language models are. It's compressing and correctly reproducing a lot of data with meaningful context between each token and the rest of the context window. It's still amazing, specially…

But that would still be copy and paste with extra steps.

Like all these vibe coded to do apps, one of the most used starting problems of programming courses.

It’s great that an AI can do that but it could stall progress if we get limited to existing tools and programs.

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

#192

Post by whimsicalism »

simonw wrote: post #165
whimsicalism wrote: post #158

Earlier quoted context omitted.

yes, all reasoning models currently are, but it’s not like ds coder or qwen coder

I don't see how the training process for GLM-4.5 is materially different from that used for Qwen3-235B-A22B-Instruct-2507 - they both did a ton of extra reinforcement learning training related to code. Am I missing something?

I think the primary thing you're missing is that Qwen3-235B-A22B-Instruct-2507 != Qwen3-Coder-480B-A35B-Instruct. And the difference there is that while both do tons of code RL, in one they do not monitor performance on anything else for forgetting/regression and focus fully on code post-training pipelines and it is not meant for other tasks.

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

#193

Post by CamperBob2 »

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]

I missed the part where he said he was going to put the Space Invaders game into production. Link?

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

#194

Post by Imustaskforhelp »

ddtaylor wrote: post #173

My brain is running legacy COBOL and first read this as > My 2.5 year old with their laptop can write Space Invaders For a few hundred milliseconds there I was thinking "these damn kids are getting good with tablets"

Don't worry I guess my brain is running bleeding edge typescript with react (I am in high school for context) and the first time I also read it this way...

But I am without my glasses, but still I have hackernews at 250%, I think I am a little cooked lol.

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

#195

Post by whimsicalism »

4b11b4 wrote: post #178
qingcharles wrote: post #164

Earlier quoted context omitted.

This. Especially if you just want to try a bunch of different things out. Renting is insanely cheap -- to the point where I don't understand how the renters are making their money back unless they stole the hardware and power. It can really help you figure a ton of things out before you blow the cash on your own hardware.

Recommended sites to rent from

runpod, vast, hyperbolic, prime intellect. if all you're doing is going to be running LLMs, you can pay per token on openrouter or some of the providers listed there

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

#196

Post by CamperBob2 »

throwworhtthrow wrote: post #156
simonw wrote: post #91

Earlier quoted context omitted.

Yesterday I used ffmpeg to extract the frame at the 13 second mark of a video out as a JPEG. If I didn't have an LLM to figure that out for me I wouldn't have done it at all.

LLM's still give subpar results with ffmpeg. For example when I asked Sonnet to trim a long video with ffmpeg, it put the input file parameter before the start time parameter, which triggers an unnecessary decode of the video file. [1] Sure, use the LLM to get over the initial hump. But ffmpeg's no exception to the rule that LLM's produce subpar code. It's worth spending a couple minutes reading the docs to understan…

That says more about suboptimal design on ffmpeg's part than it does about the LLM. Most humans can't deal with ffmpeg command lines, so it's not surprising that the LLM misses a few tricks.

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

#198

Post by bnchrch »

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]

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

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

#199

Post by skeezyboy »

svachalek wrote: post #189
skeezyboy wrote: post #179

But arent we still decades away from running our own video-creating AIs locally? Have we plateaued with this current generation of techniques?

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

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

#200

Post by qcnguy »

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?

LLM fine tuning tends to destroy the model's capabilities if you aren't very careful. It's not as easy or effective as with image generation.
Post reply on HN