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

291–300 of 415 posts

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

#291

Post by simonw »

devmor wrote: post #274
simonw wrote: post #110

Earlier quoted context omitted.

Before LLMs made ffmpeg no-longer-frustrating-to-use I genuinely didn't know that ffmpeg COULD do things like that.

I'm not really sure what you're saying an LLM did in this case. Inspired a lost sense of curiosity?

My general point is that people say things like "yeah, but this one study showed that programmers over-estimate the productivity gain they get from LLMs so how can you really be sure?"

Meanwhile I've spent the past two years constantly building and implementing things I never would have done because of the reduction in friction LLM assistance gives me.

I wrote about this first two years ago - AI-enhanced development makes me more ambitious with my projects - https://simonwillison.net/2023/Mar/27/ai-enhanced-developmen... - when I realized I was hacking on things with tech like AppleScript and jq that I'd previously avoided.

It's hard to measure the productivity boost you get from "wouldn't have built that thing" to "actually built that thing".

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

#292

Post by ben_w »

nottorp wrote: post #252
ben_w wrote: post #250

Earlier quoted context omitted.

You don't have to leave LLM code alone, it's fine to change it — unless, I guess, you're doing some kind of LLM vibe-code-golfing? But this does remind me of a previous co-worker. Wrote something to convert from a custom data store to a database, his version took 20 minutes on some inputs. Swore it couldn't possibly be improved. Obviously ridiculous because it didn't take 20 minutes to load from the old data store, n…

We all do that, sometimes where it’s time critical sometimes where it isn’t. But I keep being told “AI” is the second coming of Ahura Mazda so it shouldn’t do stuff like that right?

> Ahura Mazda

Niche reference, I like it.

But… I only hear of scammers who say, and psychosis sufferers who think, LLMs are *already* that competent.

Future AI? Sure, lots of sane-seeming people also think it could go far beyond us. Special purpose ones have in very narrow domains. But current LLMs are only good enough to be useful and potentially economically disruptive, they're not even close to wildly superhuman like Stockfish is.

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

#293

Post by pdntspa »

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?

Have you tried asking an LLM?

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

#294

Post by shortrounddev2 »

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…

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?

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

#296

Post by bob1029 »

bgirard wrote: post #258
bob1029 wrote: post #254

Earlier quoted context omitted.

This is the premise of all of the ML research I've been into. The only difference is to replace the wormhole with linear genetic programming, neuroevolution, et. al. The size of programs in the demoscene is what originally sent me down this path. The biggest question I keep asking myself - What is the Kolmogorov complexity of a binary image that provides the exact same capabilities as the current generation LLMs? Wha…

> ~100b/s of UTF8 text out of a NLP black box is this big That's not a good measure. NP problem solutions are only a single bit, but they are much harder to solve than CS2 frames for large N. If it could solve any problem perfectly, I would pay you billions for just 1b/s of UTF8 text.

> If it could solve any problem perfectly, I would pay you billions for just 1b/s of UTF8 text.

Exactly. This is what compels me to try.

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

#297

Post by simonw »

shortrounddev2 wrote: post #294
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…

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.)

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

#298

Post by wizzwizz4 »

gblargg wrote: post #118
AlexeyBrin wrote: post #5

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

The real test is if you can have it tweak things. Have the ship shoot down. Have the space invaders come from the left and right. Add two player simultaneous mode with two ships.

It can usually tweak things, if given specific instruction, but it doesn't know when to refactor (and can't reliably preserve functionality when it does), so the program gets further and further away from something sensible until it can't make edits any more.

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

#299

Post by simonw »

wizzwizz4 wrote: post #298
gblargg wrote: post #118

Earlier quoted context omitted.

The real test is if you can have it tweak things. Have the ship shoot down. Have the space invaders come from the left and right. Add two player simultaneous mode with two ships.

It can usually tweak things, if given specific instruction, but it doesn't know when to refactor (and can't reliably preserve functionality when it does), so the program gets further and further away from something sensible until it can't make edits any more.

For serious projects you can address that by writing (or having it write) unit tests along the way, that way it can run in a loop and avoid breaking existing functionality when it adds new changes.

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

#300

Post by hbn »

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 discussion I replied to was just regarding whether or not what the LLM did should be considered "engineering"

It doesn't really matter whether or not the original code was published. In fact that original source code on its own probably wouldn't be that useful, since I imagine it wouldn't have tipped the weights enough to be "recallable" from the model, not to mention it was tasked with implementing it in web technologies.

Post reply on HN