Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

z.ai

Post reply on HN
Print view View original

11–20 of 540 posts

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#11

Post by mikrl »

mythz wrote: post #5

It's looking like we'll have Chinese OSS to thank for being able to host our own intelligence, free from the whims of proprietary megacorps. I know it doesn't make financial sense to self-host given how cheap OSS inference APIs are now, but it's comforting not being beholden to anyone or requiring a persistent internet connection for on-premise intelligence. Didn't expect to go back to macOS but they're basically the…

>I know it doesn't make financial sense to self-host given how cheap OSS inference APIs are now

You can calculate the exact cost of home inference, given you know your hardware and can measure electrical consumption and compare it to your bill.

I have no idea what cloud inference in aggregate actually costs, whether it’s profitable or a VC infused loss leader that will spike in price later.

That’s why I’m using cloud inference now to build out my local stack.

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#12

Post by seaal »

tosh wrote: post #9

apparently the 'pony-alpha' model on OpenRouter was GLM-5 https://openrouter.ai/openrouter/pony-alpha z.ai tweet: https://x.com/ZixuanLi_/status/2020533168520954332

People that were tracking this were already aware but glad to have confirmation.

This blog post I was reading yesterday had some good knowledge compilation about the model.

https://blog.devgenius.io/z-ais-glm-5-leaked-through-github-...

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#14

Post by NiloCK »

mythz wrote: post #5

It's looking like we'll have Chinese OSS to thank for being able to host our own intelligence, free from the whims of proprietary megacorps. I know it doesn't make financial sense to self-host given how cheap OSS inference APIs are now, but it's comforting not being beholden to anyone or requiring a persistent internet connection for on-premise intelligence. Didn't expect to go back to macOS but they're basically the…

> Didn't expect to go back to macOS but their basically the only feasible consumer option for running large models locally.

I presume here you are referring to running on the device in your lap.

How about a headless linux inference box in the closet / basement?

Return of the home network!

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#15

Post by swalsh »

mythz wrote: post #5

It's looking like we'll have Chinese OSS to thank for being able to host our own intelligence, free from the whims of proprietary megacorps. I know it doesn't make financial sense to self-host given how cheap OSS inference APIs are now, but it's comforting not being beholden to anyone or requiring a persistent internet connection for on-premise intelligence. Didn't expect to go back to macOS but they're basically the…

Yeah that sounds great until it's running as an autonomous moltbot in a distributed network semi-offline with access to your entire digital life, and China sneaks in some hidden training so these agents turn into an army of sleeper agents.

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#17

Post by guld »

Let's hope they release it to huggingface soon.

I tried their keyboard switch demo prompt and adapted it to create a 2D Webgl-less version to use CSS, SVG and it seem to work nicely, it thinks for a very long time however. https://chat.z.ai/c/ff035b96-5093-4408-9231-d5ef8dab7261

[1] https://huggingface.co/zai-org

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#18

Post by cmrdporcupine »

Bought some API credits and ran it through opencode (model was "GLM 5").

Pretty impressed, it did good work. Good reasoning skills and tool use. Even in "unfamiliar" programming languages: I had it connect to my running MOO and refactor and rewrite some MOO (dynamic typed OO scripting language) verbs by MCP. It made basically no mistakes with the programming language despite it being my own bespoke language & runtime with syntactical and runtime additions of my own (lambdas, new types, for comprehensions, etc). It reasoned everything through by looking at the API surface and example code. No serious mistakes and tested its work and fixed as it went.

Its initial analysis phase found leftover/sloppy work that Codex/GPT 5.3 left behind in a session yesterday.

Cost me $1.50 USD in token credits to do it, but z.AI offers a coding plan which is absolutely worth it if this is the caliber of model they're offering.

I could absolutely see combining the z.AI coding plan with a $20 Codex plan such that you switch back and forth between GPT 5.3 and GLM 5 depending on task complexity or intricacy. GPT 5.3 would only be necessary for really nitty gritty analysis. And since you can use both in opencode, you could start a session by establishing context and analysis in Codex and then having GLM do the grunt work.

Thanks z.AI!

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#19

Post by Aurornis »

NiloCK wrote: post #14
mythz wrote: post #5

It's looking like we'll have Chinese OSS to thank for being able to host our own intelligence, free from the whims of proprietary megacorps. I know it doesn't make financial sense to self-host given how cheap OSS inference APIs are now, but it's comforting not being beholden to anyone or requiring a persistent internet connection for on-premise intelligence. Didn't expect to go back to macOS but they're basically the…

> Didn't expect to go back to macOS but their basically the only feasible consumer option for running large models locally. I presume here you are referring to running on the device in your lap. How about a headless linux inference box in the closet / basement? Return of the home network!

Apple devices have high memory bandwidth necessary to run LLMs at reasonable rates.

It’s possible to build a Linux box that does the same but you’ll be spending a lot more to get there. With Apple, a $500 Mac Mini has memory bandwidth that you just can’t get anywhere else for the price.

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#20

Post by resters »

swalsh wrote: post #15
mythz wrote: post #5

It's looking like we'll have Chinese OSS to thank for being able to host our own intelligence, free from the whims of proprietary megacorps. I know it doesn't make financial sense to self-host given how cheap OSS inference APIs are now, but it's comforting not being beholden to anyone or requiring a persistent internet connection for on-premise intelligence. Didn't expect to go back to macOS but they're basically the…

Yeah that sounds great until it's running as an autonomous moltbot in a distributed network semi-offline with access to your entire digital life, and China sneaks in some hidden training so these agents turn into an army of sleeper agents.

sleeper agents to do what? let's see how far you can take the absurd threat porn fantasy. I hope it was hyperbole.
Post reply on HN