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

251–260 of 415 posts

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

#251

Post by jasonvorhe »

sharkjacobs wrote: post #231
falcor84 wrote: post #74

Earlier quoted context omitted.

How come it's "not representative for real engineering"? Other than copy-pasting existing code (which is not what an LLM does), I don't see how you can create a space invaders game without applying "engineering".

Making a space invaders game is not representative of normal engineering because you're reproducing an existing game with well known specs and requirements. There are probably hundreds of thousands of words describing and discussing Space Invaders in GLM-4.5's training data It's like using an LLM to implement a red black tree. Red black trees are in the training data, so you don't need to explain or describe what you…

Smells like moving the goal post. What's real engineering to be in 2028? Implementing Google's infra stack in your homelab?

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

#252

Post by nottorp »

ben_w wrote: post #250
nottorp wrote: post #230

Earlier quoted context omitted.

Had a LLM generate 3 lines of working C++ code that was "only" one order of magnitude slower than what i edited the code to in 10 minutes. If you're happy with results like that, sure, LLMs miss "a few tricks"...

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?

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

#254

Post by bob1029 »

lxgr wrote: 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?

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? What are the chances this could run on the machine under my desk right now?

I know how many AAA frames per second my machine is capable of rendering. I refuse to believe the gap between running CS2 at 400fps and getting ~100b/s of UTF8 text out of a NLP black box is this big.

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

#256

Post by Nesco »

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…

Zuck wouldn’t have leaked it on 4chan of all the places

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

#257

Post by andai »

andai wrote: post #255

I got almost the same result with a 4B model (Qwen3-4B), about 20x smaller than OP's ~200B model. https://jsbin.com/lejunenezu/edit?html,output Its pelican was a total fail though.

Update: It failed to make Flappy Bird though (several attempts).

This surprises me, I thought it would be simpler than Space Invaders.

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

#258

Post by bgirard »

bob1029 wrote: post #254
lxgr wrote: 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?

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.

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

#259

Post by tough »

Nesco wrote: post #256
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…

Zuck wouldn’t have leaked it on 4chan of all the places

prob just told an employee to get it done no?

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

#260

Post by tough »

arkmm wrote: post #224
techwizrd wrote: post #143

Earlier quoted context omitted.

We have been fine-tuning models using Axolotl and Unsloth, with a slight preference for Axolotl. Check out the docs [0] and fine-tune or quantize your first model. There is a lot to be learned in this space, but it's exciting. 0: https://axolotl.ai/ and https://docs.axolotl.ai/

When do you think fine tuning is worth it over prompt engineering a base model? I imagine with the finetunes you have to worry about self-hosting, model utilization, and then also retraining the model as new base models come out. I'm curious under what circumstances you've found that the benefits outweigh the downsides.

only for narrow applications where your fine tune can let you use a smaller model locally , specialised and trained for your specific use-case mostly
Post reply on HN