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

ZCode – Harness for GLM-5.2

zcode.z.ai

Post reply on HN
Print view View original

341–350 of 382 posts

Re: ZCode – Harness for GLM-5.2

#341

Post by orloffm »

maxdo wrote: post #337

Interesting to see how their harness will show up here. So far, https://cursor.com/evals this even shows still a big gap in performance, and almost no real win in terms of money vs gpt5.5 and sonnet 5. Which make me raise a question. Why would I install a close source black box, that will send data to a country that you can't make legally liable for even most crazy miss doings. The market of a hosted commercial versi…

How is this different from installing Claude Code or Codex? Maybe in the US someone has some hopes about having those makers "legally liable", but in Europe both US and China products seem equally far away and equally closed in all senses.

Re: ZCode – Harness for GLM-5.2

#342

Post by real0mar »

Computer0 wrote: post #192
bitlad wrote: post #49

Earlier quoted context omitted.

OpenCode

I would agree I cannot bear to use the TUI and I find myself in the terminal quite often. The value is good on the $10 plan so I still get decent usage on the desktop client but I would prefer a better terminal interface.

You can use the opencode subscription plan with other agents if you wish. They allow it

Re: ZCode – Harness for GLM-5.2

#343

Post by maxdo »

orloffm wrote: post #341
maxdo wrote: post #337

Interesting to see how their harness will show up here. So far, https://cursor.com/evals this even shows still a big gap in performance, and almost no real win in terms of money vs gpt5.5 and sonnet 5. Which make me raise a question. Why would I install a close source black box, that will send data to a country that you can't make legally liable for even most crazy miss doings. The market of a hosted commercial versi…

How is this different from installing Claude Code or Codex? Maybe in the US someone has some hopes about having those makers "legally liable", but in Europe both US and China products seem equally far away and equally closed in all senses.

Yeah that’s why Google lost 4 billion to EU for some elusive non competitive practices. Every single big tech us company is never out of court in eu. Good luck brining any of Chinese companies for distillation . They steal your IP , your data and you have 0 protection .

Re: ZCode – Harness for GLM-5.2

#344

Post by blitzar »

ianm218 wrote: post #244
blitzar wrote: post #129

Earlier quoted context omitted.

> if you decide to go to China one day they might already have all the data PRISM ... XKeyscore ... > The US is certainly inching in that direction Itching to go in a direction that (publicly known) they have been in for decades now.

The US government is no saint in terms of mass surveillance but there is a gigantic gulf between US governments mass surveillance and China, I think to act otherwise is a bit disingenuous.

Sorry I cant take anyone who keeps a straight face while suggesting one is worse than the other.

At that point it is not disingenuous, its brain washed.

Re: ZCode – Harness for GLM-5.2

#345

Post by SwellJoe »

csomar wrote: post #216
SwellJoe wrote: post #101

Earlier quoted context omitted.

But, it's still running on my desktop/laptop. I don't trust them to run on my machine. But, I guess I could run one VM with a desktop to contain the desktop app. Or, just keep using CLI agents.

I mean, if the execution happen on the VM then the problem is trust on the programs and then you can't trust any program by that logic? That or you think AI-companies software is serious slop.

I do, in fact, think the AI companies software is serious slop. I've read some of the Claude Code source.

And, we're not talking about hypothetical attacks here. Prompt injection attacks have happened. Supply chain attacks that agents fell for have happened.

https://venturebeat.com/security/six-exploits-broke-ai-codin...

I'm going to "security in depth" these gullible little thinky guys in my computer, but you do what makes you happy.

Re: ZCode – Harness for GLM-5.2

#346

Post by 28304283409234 »

edouard-harris wrote: post #315
SwellJoe wrote: post #171

Earlier quoted context omitted.

I don't run agents directly on my desktop/laptop machine. I run them in VMs or containers (sometimes in containers on VMs). There have been too many credentials stealing exploits via prompt injection and the like for me to be willing to let an agent roam around on my personal system. I've also started creating new github deploy keys for each repo in use on a VM, so the blast area for any given agent disaster is "a co…

> The agents have sandboxes, but those are loose. Not enforced by anything outside of the agent harness itself. You might want to check out Ant's open source srt [0], I use it to contain my local coding agents. It's strict by default and enforced at the OS layer. [0] https://github.com/anthropic-experimental/sandbox-runtime

What benefit does running it locally have over parents solution of running it in a container in a VM?

I do the same: my agents run in a hardened VM on a hardened Linux machines in a separated network in my basement. The magic of ssh makes this setup transparent for me on my desktop. But extremely hard for my agent to do nasty things.

Re: ZCode – Harness for GLM-5.2

#347

Post by overgard »

ranyume wrote: post #168
cube00 wrote: post #82

It's impressive all these companies are getting away with "base usage allowance included" [1] or "standard limits" [2], layering the higher plans as a multiplier of that "base" but never disclosing what it is. I guess the base is whatever the profit margin needs to be this month. [1]: https://zcode.z.ai/en#:~:text=Base%20usage%20allowance%20inc... [2]: https://support.google.com/gemini/answer/16275805?hl=en#:~:t...

When running the app, it actually tells you what the base usages are, but the name of the plans are different from the page. It reads: Start plan: 5 Million tokens a day (GLM-5.2 3M, GLM-5 Turbo 2M) For individuals: (+150% quota) $18.00USD+ For individual developers with a dedicated Coding Plan quota.

Heh, so it sounds like you have to pay them first to find out what you're going to get for the money? That's an interesting business model..

Re: ZCode – Harness for GLM-5.2

#348

Post by kennywinker »

maxdo wrote: post #343
orloffm wrote: post #341

Earlier quoted context omitted.

How is this different from installing Claude Code or Codex? Maybe in the US someone has some hopes about having those makers "legally liable", but in Europe both US and China products seem equally far away and equally closed in all senses.

Yeah that’s why Google lost 4 billion to EU for some elusive non competitive practices. Every single big tech us company is never out of court in eu. Good luck brining any of Chinese companies for distillation . They steal your IP , your data and you have 0 protection .

If distillation is stealing, then so is generating code using an ai model. It’s the same thing: prompt a model, use the output to make software.

Not to mention, claude and gpt only exist because of massive ip theft in the first place.

Re: ZCode – Harness for GLM-5.2

#349

Post by maxdo »

kennywinker wrote: post #348
maxdo wrote: post #343

Earlier quoted context omitted.

Yeah that’s why Google lost 4 billion to EU for some elusive non competitive practices. Every single big tech us company is never out of court in eu. Good luck brining any of Chinese companies for distillation . They steal your IP , your data and you have 0 protection .

If distillation is stealing, then so is generating code using an ai model. It’s the same thing: prompt a model, use the output to make software. Not to mention, claude and gpt only exist because of massive ip theft in the first place.

yeah, sure, laws are just pointless things.

Lets move to caves and if I kill you first , i'm right, if not i lost. THat's your logic.

there is ToS, and every single person who is doing distillation knows it's illegal. Also on IP theft. There were several courts, in different countries they limit certain knowledge bases and thats it. so that entire claim is baseless.

Again this is the difference. A major book publisher brought ai companies to court and won. You can't doo anything with Chinese companies even if you are book publisher of this world.

Re: ZCode – Harness for GLM-5.2

#350

Post by yogthos »

quantumleaper wrote: post #335
yogthos wrote: post #326

Earlier quoted context omitted.

I haven't really seen anybody come up with a good test to show hard numbers on comparing agentic harnesses. It's a bit tricky to set up a definitive test given the whole non deterministic nature of LLMs. What I've been focusing on is watching the loop and seeing where model does things that it shouldn't have to. For example, I notice models doing stuff like writing python scripts to match parens for Clojure all the t…

How are you iterating on a system prompt and tool descriptions without an eval that gives you hard numbers for improvement or regression?

I look at what the model is doing in the loop and whether the harness is catching cases such as the model having to write scripts to balance parens, whether it's trying to do the same thing over and over again, and all the other cases I explained in detail in the blog post.

Even without having hard numbers, it's pretty easy to see from the log whether the model is getting stuck or not.

Post reply on HN