Very impressive model! The SVG pelican designed by GLM 4.5 in Simon's adjacent article is the most accurate I've seen yet.
My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)
161–170 of 415 posts
Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)
#162The GML-4.5 model utterly fails at creating ASCII art or factorizing numbers. It can "write" Space Invaders because there are literally thousands of open source projects out there.
This is another example of LLMs being dumb copiers that do understand human prompts.
But there is one positive side to this: If this photocopying business can be run locally, the stocks of OpenAI etc. should got to zero.
Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)
#163With the Anthropic rug pull on quotas for Max, I feel the short-mid term value sweet spot will be a Frankensteined together “Claude as orchestrator/coder, falling back to local models as quota limits approach” tool suite.
Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)
#164Apart from using a Mac, what can you use for inference with reasonable performance? Is a Mac the only realistic option at the moment?
you are almost certainly better off renting GPUs, but i understand self-hosting is an HN touchstone
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.
Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)
#165Earlier quoted context omitted.
It may not be code-only, but it was trained extensively for coding: > Our base model undergoes several training stages. During pre-training, the model is first trained on 15T tokens of a general pre-training corpus, followed by 7T tokens of a code & reasoning corpus. After pre-training, we introduce additional stages to further enhance the model's performance on key downstream domains. From my notes here: https://sim…
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?
Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)
#166The GML-4.5 model utterly fails at creating ASCII art or factorizing numbers. It can "write" Space Invaders because there are literally thousands of open source projects out there. This is another example of LLMs being dumb copiers that do understand human prompts. But there is one positive side to this: If this photocopying business can be run locally, the stocks of OpenAI etc. should got to zero.
Why would you use an LLM to factorize numbers?
Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)
#167Aside that space invaders from scratch is not representative for real engineering, it will be interesting to see what the business model for Anthropic will be if I can run a solid code generation model on my local machine (no usage tier per hour or week), let’s say, one year from now. At $200 per month for 2 years I can buy a decent Mx with 64GB (or perhaps even 128GB taking residual value into account)
The frontier models are always going to tempt you with their higher quality and quicker generation, IMO.
I’ve been mentally mapping tge models to the history of db.
Most db in the early days you had to pay for. There are still for pay db that are just better than ones you don’t pay for. Some teams think that the cost is worth the improvements and there is a (tough) business there. Fortunes were made in the early days.
But eventually open source models became good enough for many use cases and they have their own advantages. So lots of teams use them.
I think coding models might have a similar trajectory.
Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)
#168Aside that space invaders from scratch is not representative for real engineering, it will be interesting to see what the business model for Anthropic will be if I can run a solid code generation model on my local machine (no usage tier per hour or week), let’s say, one year from now. At $200 per month for 2 years I can buy a decent Mx with 64GB (or perhaps even 128GB taking residual value into account)
What about power used and support hardware ? Also card going down means you are down until you get warranty service.
why are you doing anything locally then?
Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)
#169Earlier quoted context omitted.
Except that it is not exceptional at all; it's an older-generation MacBook Pro with 64GB of RAM. There's nothing particularly unusual about it.
64 GB of RAM which is addressable by a GPU is exceptional for a laptop - this is not just system RAM.
To emphasize this point further, at least with my efforts, it is not even possible to buy a 64GB M4 Pro right now. 32GB, 64GB, and 128GB are all sold out.
We can say that 64GB addressable by a GPU is not exceptional when compared to 128GB and it still costs less than a month's pay for a FAANG engineer, but the fact that they aren't actually purchasable right now shows that it's not as easy as driving to Best Buy and grabbing one off the shelf.
Re: My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)
#170Earlier quoted context omitted.
> This is why I keep all my benchmarks private This is also why, if I were an artist or anyone commercially relying on creative output of any kind, I wouldn't be posting anything on the internet anymore, ever. The minute you make anything public, the engines will clone it to death and turn it into a commodity.
Somewhat defeats the purpose of being an artist, doesn't it?
Eeeehhhh.
Maybe the thing to do is provide public, physical exhibits of your art in search of patronage.