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

GLM 4.5 with Claude Code

docs.z.ai

Post reply on HN
Print view View original

61–70 of 90 posts

Re: GLM 4.5 with Claude Code

#61

Post by tw1984 »

partyboy wrote: post #54
arjie wrote: post #4

Okay, I'm going to try it, but why didn't you link the information on how to integrate it with Claude Code: https://docs.z.ai/scenario-example/develop-tools/claude Chinese software always has such a design language: - prepaid and then use credit to subscribe - strange serif font - that slider thing for captcha But I'm going to try it out now.

> prepaid and then use credit to subscribe This is mainly because Chinese online payment infrastructure didn't have good support for subscriptions or auto payments (at least until relatively recently) so this pattern is the norm

I have been using alipay to pay for my Tencent Video monthly subscription for the past 8-9 years.

Re: GLM 4.5 with Claude Code

#62

Post by cpursley »

sergiotapia wrote: post #23

Used it to fix a couple of bugs just now in Elixir and it runs very fast, faster than Codex with GPT-5 medium or high. This is quite nice. Will try it out a bit longer over the weekend. I tested it using Claude Code with env variables overrides.

Good the hear it’s competent with Elixir! How would you compare it to Claude?

Re: GLM 4.5 with Claude Code

#63

Post by unsupp0rted »

aurareturn wrote: post #60
unsupp0rted wrote: post #48

Anthropic can't compete with this on cost. They're probably bleeding money as it is. But they can sort of compete on model quality, by no longer dumbing down their models. That'll be expensive too, but it's a lever they have.

One of the articles posted here a week ago says Claude Code has about a ~20x margin on inference. So they can compete on cost if they want.

Is Claude Code enterprise usage keeping the rest of the company afloat and able to keep raising?

Re: GLM 4.5 with Claude Code

#64

Post by conradev »

The graphs that some of these companies make are brutal: https://docs.z.ai/guides/llm/glm-4.5#higher-parameter-effici...

"So, we only know the Y-axis for some models in the scatter plot. Let's make up an X-axis value on the bad side of the graph and include the data points anyway."

Visually disingenuous!

Re: GLM 4.5 with Claude Code

#65

Post by croemer »

conradev wrote: post #64

The graphs that some of these companies make are brutal: https://docs.z.ai/guides/llm/glm-4.5#higher-parameter-effici... "So, we only know the Y-axis for some models in the scatter plot. Let's make up an X-axis value on the bad side of the graph and include the data points anyway." Visually disingenuous!

Which x axis was made up? You mean showing barplots in descending order of scores?

Re: GLM 4.5 with Claude Code

#66

Post by d4rkp4ttern »

arjie wrote: post #4

Okay, I'm going to try it, but why didn't you link the information on how to integrate it with Claude Code: https://docs.z.ai/scenario-example/develop-tools/claude Chinese software always has such a design language: - prepaid and then use credit to subscribe - strange serif font - that slider thing for captcha But I'm going to try it out now.

For models available via Anthropic-compatible (currently Kimi-K2, GLM, Deepseek), the simplest way to use them with CC is by setting up a function in .zshrc:

https://github.com/pchalasani/claude-code-tools/tree/main?ta...

Surprised that Qwen didn’t do the same, (though I know they have their own CLI-coding agent).

Re: GLM 4.5 with Claude Code

#67

Post by diggan »

Szpadel wrote: post #40
arjie wrote: post #4

Okay, I'm going to try it, but why didn't you link the information on how to integrate it with Claude Code: https://docs.z.ai/scenario-example/develop-tools/claude Chinese software always has such a design language: - prepaid and then use credit to subscribe - strange serif font - that slider thing for captcha But I'm going to try it out now.

you can use any model with Claude code thanks to https://github.com/musistudio/claude-code-router but in my testing other models do not work well, looks like prompts are either very optimized for Claude, or other models are just not great yet with such agentic environment I was especially disappointed with grok code. it is very fast as advertised but in generating spaces and new lines in function calling until it hit…

> but in my testing other models do not work well, looks like prompts are either very optimized for Claude, or other models are just not great yet with such agentic environment

I think there are multiple things going on. First, models are either trained with tool calling in mind or not, the ones that don't, won't work well as agents. Secondly, each companies models are trained with the agent software in mind, and the agent software is built with their specific models in mind. Thirdly, each model responds differently to different system/user prompts, and the difference can be really stark.

I'm currently working on a tool that lets me execute the same prompts with the same environment over multiple agents. Currently I'm running Codex, Claude Code, Gemini, Qwen Code and AMP for every single change, just to see the differences in responses, and even reusing the same system prompt across all of them gives wildly different results. Not to mention how quickly the quality drops off the cliff as soon as you switch out any non-standard model for any of those CLIs. Mix-and-match models between those five tools, and it becomes clear as day that the modelsoftware is more interlocked than it seems.

The only project I've had success with switching out the model of, has been using GPT-OSS-120b locally with Codex, but that still required me to manually hack in support for changing the temperature, and changing the prompts Codex use a bit, to get OK results.

Re: GLM 4.5 with Claude Code

#68

Post by saretup »

Surprised to see no one here is worried about privacy. Z.ai's privacy policy pretty much allows them to store and use prompts/code in a perpetual, irrevocable, worldwide, sublicensable license to use and train their models.
Post reply on HN