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

GLM-5.3: Frontier coding with emergent cyber capabilities

z.ai

Post reply on HN
Print view View original

561–570 of 626 posts

Re: GLM-5.3: Frontier coding with emergent cyber capabilities

#561

Post by stogot »

computerex wrote: post #520
weego wrote: post #489

Earlier quoted context omitted.

what is a harness? The comments below are mixing IDE/ADE but other suggestions are purely terminal things and I don't get what their value is over just a terminal. Is a harness like a loop where it's just a vague thing that everyone nods about but everyone is nodding at something different?

The harness is the agent. LLM's can be asked to output things in JSON for example. The LLM then literally asks for things like "execute this cmd" or search/replace this string. The LLM outputs text, but in a deterministic format that can be parsed. The harness calls the LLM, exposes tools, executes tools the LLM asks for, gates tool use based on security controls. It's the runtime that the agent uses to do work.

Are the LLM and agent the same thing? Why different nouns ?

Re: GLM-5.3: Frontier coding with emergent cyber capabilities

#562

Post by yogthos »

johng wrote: post #544
yogthos wrote: post #376

Earlier quoted context omitted.

I'm gonna shamelessly plug my own here :) https://dirge-code.github.io/

I get hung here on Debian 13 after installing rustup and doing rustup install stable. Building [=======================> ] 610/611: dirge(bin) Just hangs there :(

might just be slow, it can take over 5 min to compile

Re: GLM-5.3: Frontier coding with emergent cyber capabilities

#563

Post by computerex »

stogot wrote: post #561
computerex wrote: post #520

Earlier quoted context omitted.

The harness is the agent. LLM's can be asked to output things in JSON for example. The LLM then literally asks for things like "execute this cmd" or search/replace this string. The LLM outputs text, but in a deterministic format that can be parsed. The harness calls the LLM, exposes tools, executes tools the LLM asks for, gates tool use based on security controls. It's the runtime that the agent uses to do work.

Are the LLM and agent the same thing? Why different nouns ?

The LLM is the core model, but the harness has the prompts/tool definitions, guidance/recovery/correction code. The harness itself is the agent, because same model may perform vastly differently on different harnesses. Agent is the system working as a whole, harness+llm.

Re: GLM-5.3: Frontier coding with emergent cyber capabilities

#564

Post by chrisweekly »

redeeman wrote: post #540
badcafe23423435 wrote: post #480

Earlier quoted context omitted.

No one in their right mind would install software using `curl | bash`

its a good way to check if people are insane though. would be a cool tactic for new hire evaluation, monitor them setting up dev environment. do the curl | bash, and its instafail

In countless corporate environments (including in highly regulated industries), far from being a firable offense, piping curl to bash is often a prescribed step in setting up the standard dev env. The cognitive dissonance is soul crushing. Maybe they're testing for one's ability to tolerate it.

Re: GLM-5.3: Frontier coding with emergent cyber capabilities

#565

Post by ziiinq »

gigatexal wrote: post #541
vorticalbox wrote: post #505

Earlier quoted context omitted.

It’s not just bloat at this point. I run oMLX and run models locally. using Claude code on the first message dumps 40k of tokens that my laptop takes 5 mins to compute. I’ve stopped using it completely now.

Did you build you own harness? I would miss skills and all the ecosystem if I did the same no?

[dead]

Re: GLM-5.3: Frontier coding with emergent cyber capabilities

#566

Post by leobuskin »

clbrmbr wrote: post #556
leobuskin wrote: post #305

I bought $18 GLM official subscription yesterday (5.2, but new model version was already leaking on some docs), set it up with Claude Code harness... and I’ve bumped to $80 plan almost immediately. It’s the first model that agreed on a proper security research (red team scenario), executed it seamlessly, including 0-days in WP plugins, RCE, 6.8 kernel exploit adaptation, etc - while playing against another GLM agent…

How are you using it in Claude Code? What is the native harness that GLM was post-trained in?

That’s the first model that fits CC as it’s own, zero issues, but probably ZCode or whatever z.ai’s cli is.

Re: GLM-5.3: Frontier coding with emergent cyber capabilities

#568

Post by LoganDark »

weego wrote: post #489
rattlesnakedave wrote: post #324

Earlier quoted context omitted.

You should try a better harness. Try pi, or ohmypi if you want a good OOB experience

what is a harness? The comments below are mixing IDE/ADE but other suggestions are purely terminal things and I don't get what their value is over just a terminal. Is a harness like a loop where it's just a vague thing that everyone nods about but everyone is nodding at something different?

A harness is the tooling around an LLM that uses its responses to do work. For example, let's say a harness sends your message to the LLM and the LLM emits a tool call - the harness is responsible for processing that tool call, executing the tool, and then sending its response back to the LLM to get more of its turn. The harness is responsible for keeping the conversation history to send back to the LLM each time it needs more completion. The harness is responsible for displaying the user interface that allows you to send instructions to the LLM or configure MCP servers or whatever. Claude Code is a harness, Pi is a harness, OpenCode is (technically) a harness, it's basically the LLM "client". The model is what generates the completions itself, but the harness is how you invoke it. And generally when people say "agent" they mean the harness hooked up to some model.

Re: GLM-5.3: Frontier coding with emergent cyber capabilities

#569

Post by cheema33 »

eru wrote: post #258
Gigachad wrote: post #124

Earlier quoted context omitted.

This is going to be catastrophic. Whether AI works or is useful or not isn’t even the question anymore. It can fulfil every promise Sam Altman has been making and will still make no financial sense to justify these valuations.

Why is anything going to be catastrophic? Companies can go bankrupt without catastrophes for the rest of us. Happens all the time.

> Why is anything going to be catastrophic?

Many believe, including myself, that the market is currently propped by a massive AI bubble. Nearly a US $1 trillion is being spent this year, and more is planned for next year. All of this is for a "build up". There is no pay out. The major AI companies are taking in massive losses in the hopes that they will eventually be able to cash out.

The math is not looking good to me. The effect will be like the dotcom bubble. But much much bigger. Because the numbers are so much bigger.

Re: GLM-5.3: Frontier coding with emergent cyber capabilities

#570

Post by spaceman_2020 »

brynnbee wrote: post #497
spaceman_2020 wrote: post #242

Earlier quoted context omitted.

Your tools refusing to do your bidding is an absurd idea in the first place Imagine asking for permission to use your hammer

I mean I don't want autonomous cars to follow directions by humans that sound like "plow into this crowd of people". Even things like microwaves don't let you turn it on without the door closed. I don't see how this is any different.

This is why you can't leave judgment to technology, and why we have law enforcement and courts

"Plow into this crowd of people" is nominally wrong, but what if its actually "plow into this crowd of people that are hurting and robbing a family with two small children"

Your smart hammer refuses to let you smash into a glass window, but what if you were smashing into the glass window to save a child stuck in a fire?

Post reply on HN