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

181–190 of 415 posts

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

#181

Post by sarchertech »

falcor84 wrote: post #68
bayindirh wrote: post #61

Earlier quoted context omitted.

Humans can observe ants and invent any colony optimization. AIs can’t. Humans can explore what they don’t know. AIs can’t.

What makes you categorically say that "AIs can't"? Based on my experience with present day AIs, I personally wouldn't be surprised at all that if you showed Gemini 2.5 Pro a video of an insect colony and asked it "Take a look at the way they organize and see if that gives you inspiration for an optimization algorithm", it will spit something interesting out.

It will 100% have something in its training set discussing a human doing this and will almost definitely spit out something similar.

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

#182

Post by th0ma5 »

simonw wrote: post #35
larodi wrote: post #28

Is probably more correct to say - my 2.5 year laptop can RETELL space invaders. Pretty sure it cannot write a game it has never seen, so you can even say - my old laptop can now do this fancy extraction of data from a smart probabilistic blob, where the original things are retold in new colours and forms :)

I know these models can build games and apps they've never seen before because I've already observed them doing exactly that time and time again. If you haven't seen that yourself yet I suggest firing up the free, no registration required GLM-4.5 Air on https://chat.z.ai/ and seeing if you can prove yourself wrong.

[flagged]

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

#183

Post by svachalek »

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?

For completeness, for Apple hardware MLX is the way to go.

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

#185

Post by doormatt »

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.io

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

#187

Post by simonw »

bgwalter wrote: post #176
simonw wrote: post #166

Earlier quoted context omitted.

Why would you use an LLM to factorize numbers?

Because we are told that they can solve IMO problems. Yet they fail at basic math problems, not only at factorization but also when probing them with relatively basic symbolic math that would not require the invocation of an external program. Also, you know it they fail they could say so instead of giving a hallucinated answer. First the models lie and say that a 20 digit number takes vast amounts of computing. Then,…

That's why the IMO results were so notable: that was one of those moments where new models were demonstrated doing something that they had previously been unable to do.

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

#189

Post by svachalek »

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?

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

#190

Post by syntaxing »

techwizrd wrote: post #143
genewitch wrote: post #96

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?

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/

What hardware do you train on using axolotl? I use unsloth with Google colab pro
Post reply on HN