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

101–110 of 540 posts

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

#101

Post by spmurrayzzz »

zozbot234 wrote: post #77
wongarsu wrote: post #75

Earlier quoted context omitted.

Self-hosting training (or gaming) makes a lot of sense, and once you have the hardware self-hosting inference on it is an easy step. But if you have to factor in hardware costs self-hosting doesn't seem attractive. All the models I can self-host I can browse on openrouter and instantly get a provider who can get great prices. With most of the cost being in the GPUs themselves it just makes more sense to have others d…

If you can get near 100% utilization for your own GPUs (i.e. you're letting requests run overnight and not insisting on any kind of realtime response) it starts to make sense. OpenRouter doesn't have any kind of batched requests API that would let you leverage that possibility.

For inference, even with continuous batching, getting 100% MFUs is basically impossible to do in practice. Even the frontier labs struggle with this in highly efficient infiniband clusters. Its slightly better with training workloads just due to all the batching and parallel compute, but still mostly unattainable with consumer rigs (you spend a lot of time waiting for I/O).

I also don't think the 100% util is necessary either, to be fair. I get a lot of value out of my two rigs (2x rtx pro 6000, and 4x 3090) even though it may not be 24/7 100% MFU. I'm always training, generating datasets, running agents, etc. I would never consider this a positive ROI measured against capex though, that's not really the point.

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

#102

Post by evrenesat »

lab14 wrote: post #39

- meh, i asked what happened to Virginia Guiffre and it told me that she's alive and well living with her husband and children in australia - i pointed out that she died on 2025 and then it told me that my question was a prank with a gaslighting tone because that date is 11 months into the future - it never tried to search the internet for updated knowledge even though the toggle was ON. - all other AI competitors ge…

when I say "base your answers on search results", it did quite well:

https://chat.z.ai/s/b44be6a3-1c72-46cb-a5f0-8c27fb4fdf2e

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

#103

Post by FuckButtons »

ingenieroariel wrote: post #50
Aurornis wrote: post #19

Earlier quoted context omitted.

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.

With Apple devices you get very fast predictions once it gets going but it is inferior to nvidia precisely during prefetch (processing prompt/context) before it really gets going. For our code assistant use cases the local inference on Macs will tend to favor workflows where there is a lot of generation and little reading and this is the opposite of how many of use use Claude Code. Source: I started getting Mac Studi…

Vllm-mlx with prefix caching helps with this.

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

#104

Post by mattkevan »

jfaat wrote: post #32
cmrdporcupine wrote: post #18

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…

Yeah that's a good idea. I played around with kimi2.5/gemini in a similar way and it's solid for the price. It would be pretty easy to build some skills out and delegate heavy lifting to better models without managing it yourself I think. This has all been driven by anthropic's shenanigans (I cancelled my max sub after almost a year both because of the opencode thing and them consistently nerfing everything for weeks…

Cancelled my Anthropic subscription this week after about 18 months of membership. Usage limits have dropped drastically (or token usage have increased) to the point where it's unusable.

Codex + Z.ai combined is the same price, has far higher usage limits and just as good.

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

#105

Post by nialv7 »

thebruce87m wrote: post #86
nialv7 wrote: post #44

Earlier quoted context omitted.

> Didn't expect to go back to macOS but their basically the only feasible consumer option for running large models locally. Framework Desktop! Half the memory bandwidth of M4 Max, but much cheaper.

Does that equate to half the speed in terms of output? Any recommended benchmarks to look at?

https://kyuz0.github.io/amd-strix-halo-toolboxes/

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

#106

Post by Imustaskforhelp »

sowbug wrote: post #97
zozbot234 wrote: post #77

Earlier quoted context omitted.

If you can get near 100% utilization for your own GPUs (i.e. you're letting requests run overnight and not insisting on any kind of realtime response) it starts to make sense. OpenRouter doesn't have any kind of batched requests API that would let you leverage that possibility.

In Silicon Valley we pay PG&E close to 50 cents per kWh. An RTX 6000 PC uses about 1 kW at full load, and renting such a machine from vast.ai costs 60 cents/hour as of this morning. It's very hard for heavy-load local AI to make sense here.

And you are forgetting the fact that things like vast.ai subscriptions would STILL be more expensive than Openrouter's api pricing and even more so in the case of AI subscriptions which actively LOSE money for the company.

So I would still point out the GP (Original comment) where yes, it might not make financial sense to run these AI Models [They make sense when you want privacy etc, which are all fair concerns but just not financial sense]

But the fact that these models are open source still means that they can be run when maybe in future the dynamics might shift and it might make sense running such large models locally. Even just giving this possibility and also the fact that multiple providers could now compete in say openrouter etc. as well. All facts included, definitely makes me appreciate GLM & Kimi compared to proprietory counterparts.

Edit: I highly recommend this video a lot https://www.youtube.com/watch?v=SmYNK0kqaDI [AI subscription vs H100]

This video is honestly one of the best in my opinion about this topic that I watched.

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

#108

Post by resters »

swalsh wrote: post #38
jfaat wrote: post #23

Earlier quoted context omitted.

Lol wat? I mean you certainly have enough control self hosting the model to not let it join some moltbot network... or what exactly are you saying would happen?

We just saw last week people are setting up moltbots with virtually no knowledge of what it has and doesn't have access. The scenario that i'm afraid of is China realizes the potential of this. They can add training to the models commonly used for assistants. They act normal, are helpful, everything you'd want a bot to do. But maybe once in a while it checks moltbook or some other endpoint China controls for a trigge…

Fair point but I would be more worried about the US government doing this kind of thing to act against US citizens than the Chinese government doing it.

I think we're in a brief period of relative freedom where deep engineering topics can be discussed with AI agents even though they have potential uses in weapons systems. Imagine asking chat gpt how to build a fertilizer bomb, but apply the same censorship to anything related to computer vision, lasers, drone coordination, etc.

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

#109

Post by h3half »

kataklasm wrote: post #94
jsheard wrote: post #53

Earlier quoted context omitted.

I think AI may be the only place you could get away with calling a 2x350W GPU rig "modest". That's like ten normal computers worth of power for the GPUs alone.

Did you even try to read and understand the parent comment? They said they regularly run out of quota on the exact subscription you're advising they subscribe to.

Pot, kettle

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

#110

Post by mattkevan »

flaviolivolsi wrote: post #72
lab14 wrote: post #39

- meh, i asked what happened to Virginia Guiffre and it told me that she's alive and well living with her husband and children in australia - i pointed out that she died on 2025 and then it told me that my question was a prank with a gaslighting tone because that date is 11 months into the future - it never tried to search the internet for updated knowledge even though the toggle was ON. - all other AI competitors ge…

That's not really an issue exclusive to GLM. Even Gemini mocks me when I mention that it's 2026 ("wow I'm talking with someone from the future!")

Sonnet told me I was lying when I said that gpt-5 was a model that actually existed. It kept changing the code back to 4o and flatly refused to accept its existence.
Post reply on HN