Live data from Hacker News

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

simonwillison.net

371–380 of 415 posts

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

#371
Standalone mini projects like that are also a good way to train students. But I believe LLMs are still a far long path away from being able to solve problems that require combination solutions like different environments, software, circumstances, projects, ...

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

#372
post #227

This raises an interesting question I’ve seen occasionally addressed in science fiction before: Could today’s consumer hardware run a future superintelligence (or, as a weaker hypothesis, at least contain some lower-level agent that can bootstrap something on other hardware via networking or hyperpersuasion) if the binary dropped out of a wormhole?

could today's seemingly "superintelligence" models run on 10-20 years old hardware? probably it works.

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

#373
post #225

Earlier quoted context omitted.

I'd hope most professional software engineers could do this in an afternoon or so?

Depends on the rules. Can I look up other space invaders games on github first? Can I use a game framework? Just JS / HTML docs I probably could not.

No preexisting framework.

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

#374
post #140

Earlier quoted context omitted.

They may be, but there are lots of languages, lots of approaches, lots of methodologies and just a ton of different ways to "code", coding isn't one homogeneous activity that one model beats all the other models at. > what specific tasks is one performing better than the other? That's exactly why you create your own benchmark, so you can figure that out by just having a list of models, instead of testing each individ…

> coding isn't one homogeneous activity that one model beats all the other models at If you can't even replace one coding model with another, it's hard to imagine you can replace human coders with coding models.

What you mean "can't even replace"? You can, nothing in my comment says you cannot?

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

#375
post #200

Earlier quoted context omitted.

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.

My very cursory understanding -- at least from Unsloth's recommendations -- is that you have to work very hard to preserve reasoning/instruct capabilities [1]: for example to "preserve" Qwen3's reasoning capabilities (however that's operationalized), they suggest a fine-tuning corpus that's 75% chain of thought to 25% non-reasoning. Is that a significant issue for orgs/projects that currently rely on fine-tuning?

[1] https://docs.unsloth.ai/basics/qwen3-how-to-run-and-fine-tun...

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

#376

I initially read the title as "My 2.5 year old can write Space Invaders in JavaScript now (GLM-4.5 Air)." Though I suppose, given a few years, that may also be true!

Given a few years your 2.5 year old will be a 5.5 year old, too!

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

#377

Earlier quoted context omitted.

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.)

Where do we speak about it? It feels like the biggest use for these models right now is for deep fakes and other harassment but few people in the industry want to talk about it while continuing to enable it.

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

#378
post #140

Earlier quoted context omitted.

They may be, but there are lots of languages, lots of approaches, lots of methodologies and just a ton of different ways to "code", coding isn't one homogeneous activity that one model beats all the other models at. > what specific tasks is one performing better than the other? That's exactly why you create your own benchmark, so you can figure that out by just having a list of models, instead of testing each individ…

> coding isn't one homogeneous activity that one model beats all the other models at If you can't even replace one coding model with another, it's hard to imagine you can replace human coders with coding models.

You probably can't replace a seasoned COBOL programmer with a seasoned Haskell programmer. Does that mean that either person is bad at programming as a whole?

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

#379
post #200

Earlier quoted context omitted.

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.

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

These are now questions at the cutting edge of academic research. It might be computationally unknowable until checked.

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

#380

Earlier quoted context omitted.

“useful things“ like poorly drawing birds on bikes? ;) (I have much respect for what you have done and are currently doing, but you did walk right into that one)

The pelican on a bicycle is a very useful test.

Yeah what if you need a drawing of a pelican on a bicycle
Post reply on HN