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

171–180 of 382 posts

Re: ZCode – Harness for GLM-5.2

#171

Post by SwellJoe »

scorpioxy wrote: post #151
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.

Is the trust concern for the agent running in any form on your machine? Like in a VM on your machine as well or do you mean on the host itself? I have read about people giving an agent full access to their main system saying they have nothing of value. To me, that's a strange opinion to have with the distinction between what's private and what's secret.

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 couple/few github repos and whatever credentials were needed for the agent/model".

I wouldn't let a coworker, even one I know pretty well, log into my personal account on my machines...why would I let an agent that can be tricked into uploading all my credentials to an attackers web server?

The agents have sandboxes, but those are loose. Not enforced by anything outside of the agent harness itself.

Re: ZCode – Harness for GLM-5.2

#172

Post by ahmadyan »

SwellJoe wrote: post #29
seizethecheese wrote: post #11

I'm somewhat surprised that this is not open source (from what I can tell). Compare to Mimo Code https://github.com/XiaomiMiMo/MiMo-Code (which is a CLI, while this is a desktop app).

I don't even know what I would do with a desktop app. I'm running these things in headless VMs, so I can run them with `--dangerously-skip-permissions` or whatever. I don't trust them, even without that flag, on my desktop/laptop.

a well-design IDE should abstract that away, i.e. run the agent in the headless VMs while give you an abstraction that you would feel like you are running the agent locally with all the benefits (editor, browser, diffs, debugger, etc)

Re: ZCode – Harness for GLM-5.2

#173

Post by ghm2199 »

SwellJoe wrote: post #101
teaspoon wrote: post #71

Earlier quoted context omitted.

Good desktop apps in this category can manage agents across any number of remote SSH hosts.

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.

For local tasks you can only give agents delegated that execute your deterministic read or write on an allowed set of files(e.g pi does this) and execute rights only on containers with no network access. That should get you 95% unblocked for most tasks you want to do with an LLM pretty safely.

You can do a brainstorming with web on a remote container prototyping based on that brainstorm on another container with no network access.

The one thing that is less trustworthy is using local agents for service management, you definitely want to have them scoped to dev/testing. I would never trust an agent to execute any command in production or sensitive data at all

Re: ZCode – Harness for GLM-5.2

#175

Post by MarceloHenry »

Can anyone tell me if Z.AI's cheapest plan is more or less generous than Claude's cheapest plan? If it is more or less generous, could you describe the extent of the difference?

(If this comment is too formal, I'm sorry. I used Google Translate to it [this line was NOT translated])

Re: ZCode – Harness for GLM-5.2

#176

Post by zackify »

MarceloHenry wrote: post #175

Can anyone tell me if Z.AI's cheapest plan is more or less generous than Claude's cheapest plan? If it is more or less generous, could you describe the extent of the difference? (If this comment is too formal, I'm sorry. I used Google Translate to it [this line was NOT translated])

I got around 17m tokens on glm 5.2 then blocked for 4 days on the weekly limit on that plan.

Re: ZCode – Harness for GLM-5.2

#177

Post by galaxyLogic »

ahrzb wrote: post #108
maxloh wrote: post #51

I don't find a closed-source Chinese agent system trustworthy. It is essentially a black box with full user permissions, meaning you are just handing over your entire system to a Chinese-owned server. With OpenCode and its GLM provider, at least I can monitor which files were read, which were edited, and what commands were executed. Not to mention that Chinese national security laws legally obligate companies to coop…

At least the model weights are open, I’m not American, so to me this is much more trustworthy in every possible way. You’re talking as if US intelligence are the good guys, and to me at least, they are not to any extent.

What can you gain by looking at the weights, whether open source or not? Are they not what determines the model's output, but in an oblique way? We can't really fix the weights ourselves, weight by weight, or can we?

Re: ZCode – Harness for GLM-5.2

#178

Post by notshore »

SwellJoe wrote: post #171
scorpioxy wrote: post #151

Earlier quoted context omitted.

Is the trust concern for the agent running in any form on your machine? Like in a VM on your machine as well or do you mean on the host itself? I have read about people giving an agent full access to their main system saying they have nothing of value. To me, that's a strange opinion to have with the distinction between what's private and what's secret.

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…

I'm working on a credential broker that would keep credentials vaulted and parcel out access on a per-grant basis. Is that something you'd find useful or is your setup comprehensive enough? We would be allowing people to draft access policies with natural language, I figured it would be useful for things like vercel, stripe access etc.

Re: ZCode – Harness for GLM-5.2

#179

Post by MarceloHenry »

zackify wrote: post #176
MarceloHenry wrote: post #175

Can anyone tell me if Z.AI's cheapest plan is more or less generous than Claude's cheapest plan? If it is more or less generous, could you describe the extent of the difference? (If this comment is too formal, I'm sorry. I used Google Translate to it [this line was NOT translated])

I got around 17m tokens on glm 5.2 then blocked for 4 days on the weekly limit on that plan.

17M tokens... I think it is a lot. What were you working on?

Re: ZCode – Harness for GLM-5.2

#180

Post by tekacs »

subarctic wrote: post #148
scotty79 wrote: post #100

Earlier quoted context omitted.

Which makes keeping Codex closed source look even sillier. Software is no longer anyone's moat. Just let it go.

I thought codex was open source https://github.com/openai/codex

The CLI / engine is, the desktop app and its plugins (e.g. computer use) are not.
Post reply on HN