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

GLM-5.2 is a step change for open agents

interconnects.ai

Post reply on HN
Print view View original

11–20 of 240 posts

Re: GLM-5.2 is a step change for open agents

#11

Post by themgt »

I just tested GLM 5.2 out via Z.ai in pi for a little one-off project that was already scoped. It actually did a relatively decent job starting out, and figured important things out from context.

But the reasoning traces became increasingly hilarious, with it getting confused and going in loops, doubting itself. I began to feel almost sad, it was like listening to the internal monologue of someone with anxiety disorder.

It made pretty good progress but wound up going in a lot of goofy loops and doing things a bit "off" from standards I'd hoped it would infer, and finally started going a bit nuts, "This is very confusing.", "OH WAIT", seemingly hallucinating a whole side-quest that didn't make sense and looking at making internal system changes to try to achieve its (now very confused) goal when I pulled the plug.

Without seeing the reasoning traces from Claude/GPT it's hard to really know, but it definitely didn't feel like the same quality of reasoning, even if dogged persistence does wind up actually working eventually.

Re: GLM-5.2 is a step change for open agents

#12

Post by ceejayoz »

Balinares wrote: post #2

I can't help wondering what kind of models we'll see coming out of China once it gets its own chip fabs up and running. Right now it sounds like the US's export ban is not slowing them down a whole lot.

> Right now it sounds like the US's export ban is not slowing them down a whole lot.

It may wind up being a massive boost to them in the long run, even.

Necessity is the mother of invention.

Re: GLM-5.2 is a step change for open agents

#13

Post by pkroll »

ceejayoz wrote: post #12
Balinares wrote: post #2

I can't help wondering what kind of models we'll see coming out of China once it gets its own chip fabs up and running. Right now it sounds like the US's export ban is not slowing them down a whole lot.

> Right now it sounds like the US's export ban is not slowing them down a whole lot. It may wind up being a massive boost to them in the long run, even. Necessity is the mother of invention.

If this pans out, you're not at all kidding: https://www.youtube.com/watch?v=8ekndZwyOzo

Re: GLM-5.2 is a step change for open agents

#14

Post by jauntywundrkind »

themgt wrote: post #11

I just tested GLM 5.2 out via Z.ai in pi for a little one-off project that was already scoped. It actually did a relatively decent job starting out, and figured important things out from context. But the reasoning traces became increasingly hilarious, with it getting confused and going in loops, doubting itself. I began to feel almost sad, it was like listening to the internal monologue of someone with anxiety disord…

I think the self-doubt might actually be a very crucial part of it's capability. I often feel compelled to interrupt when I'm watching it think (which thank the stars it let's us do, unlike the big American models!!), but usually it makes the right pick!

Being willing and able to reconsider seems very good. Going around and around, pulling in more thinking, integrating it: maybe that's why it is as good as it's good.

I want to emphasize again how excellent it is that we can see the thinking. I think this makes GLM so much better an experience for me. It gives me such insight into what is being considered, helps me see where things go wrong. It grounds me, gives me the notion of where the results come from. It was so jarring to switch to GPT and Opus and find that they won't discuss with me, won't reveal their thinking: that feels fundamentally unsafe, for me, for society, to have such a severe black box. I don't think it should be allowed, honestly.

Many thanks to this recent submission, which is the first time I've seen anyone blog about this core difference: The text in Claude Code’s “Extended Thinking” output is not authentic. https://patrickmccanna.net/the-text-in-claude-codes-extended... https://news.ycombinator.com/item?id=48630535

Re: GLM-5.2 is a step change for open agents

#15

Post by citizenpaul »

Ive been using glm5 since its release and still prefer it to glm5.1 and so far to glm5.2

Perhaps it is just my harness and workflow, but the older model still seems to work better. Also the token cost is significantly lower. I rarely spend more than $20 a week with $50 cap. Not even half claudes ambiguous minimum $200 a month plan.

Re: GLM-5.2 is a step change for open agents

#16

Post by uberex »

ttoinou wrote: post #4
jerojero wrote: post #3

Open weight models from Chinese labs tend to be significantly cheaper. I think theyre absolutely needed. I can't afford 200 USD a month for personal use of coding AI, and I don't think such prices are reasonable for most of the world economy anyway. Not to mention US firms might be giving their employees a lot more than that. It's increasingly feeling, to me, that theres a gap building up between haves and have nots.…

200 is much less than the value you’re supposed to get out of it. If it’s not then yeah go ahead and use cheaper models with worst quality

Unless that value is $200 cash in hand it will be hard to afford it for people who just don't have $200.

Re: GLM-5.2 is a step change for open agents

#17

Post by holoduke »

Dayshine wrote: post #5
ttoinou wrote: post #4

Earlier quoted context omitted.

200 is much less than the value you’re supposed to get out of it. If it’s not then yeah go ahead and use cheaper models with worst quality

I'm not sure how I'm supposed to get $200 of value out of personal use!

Here most of my colleagues have +200 dollar rates. It's really a no brainer. But sure, in south America or some Asian countries maybe it is. But still most devs need it anyway. Also in the poor regions.

Re: GLM-5.2 is a step change for open agents

#18

Post by wuhhh »

jauntywundrkind wrote: post #14
themgt wrote: post #11

I just tested GLM 5.2 out via Z.ai in pi for a little one-off project that was already scoped. It actually did a relatively decent job starting out, and figured important things out from context. But the reasoning traces became increasingly hilarious, with it getting confused and going in loops, doubting itself. I began to feel almost sad, it was like listening to the internal monologue of someone with anxiety disord…

I think the self-doubt might actually be a very crucial part of it's capability. I often feel compelled to interrupt when I'm watching it think (which thank the stars it let's us do, unlike the big American models!!), but usually it makes the right pick! Being willing and able to reconsider seems very good. Going around and around, pulling in more thinking, integrating it: maybe that's why it is as good as it's good.…

Your post made me laugh because I experienced the same as you but the other way around. I switched from Claude to a multi model harness a couple of days ago and the first model I tried was GLM5.2.

I gave it some simple code porting exercises and watched dumbfounded at the reasoning, which was more like the ravings of a lunatic - but lo and behold, after much confusion and a dizzying number of eureka moments the task was completed very successfully.

I tried Kimi on a similar task, much faster, a little more reassuring somehow in its ramblings, also surprisingly good results.

To be clear, I’m not surprised the results were good because they’re not GPT or Claude, but because the line of reasoning was so bonkers. Coming from Claude, I was just not used to seeing this, but I’ll bet it’s just as nuts with the frontier models and we’re just not allowed to see it (I’m about to read the links you shared).

Agree wholeheartedly that transparency is of grave importance.

Re: GLM-5.2 is a step change for open agents

#19

Post by HDBaseT »

holoduke wrote: post #17
Dayshine wrote: post #5

Earlier quoted context omitted.

I'm not sure how I'm supposed to get $200 of value out of personal use!

Here most of my colleagues have +200 dollar rates. It's really a no brainer. But sure, in south America or some Asian countries maybe it is. But still most devs need it anyway. Also in the poor regions.

$200/h is on the extreme end and I would argue most people here aren't anywhere close to that.

The median hourly wage in the US is $28/h, this equates to nearly 7.5 hours. A full day of work a month for the average person to use Claude with reasonable limits.

Yes, the people on $28/h may not be the software development types, so their income might not be as high, but these are the people who would probably be vibe coding the most since they aren't day to day programmers!

Re: GLM-5.2 is a step change for open agents

#20

Post by smrtinsert »

ttoinou wrote: post #4
jerojero wrote: post #3

Open weight models from Chinese labs tend to be significantly cheaper. I think theyre absolutely needed. I can't afford 200 USD a month for personal use of coding AI, and I don't think such prices are reasonable for most of the world economy anyway. Not to mention US firms might be giving their employees a lot more than that. It's increasingly feeling, to me, that theres a gap building up between haves and have nots.…

200 is much less than the value you’re supposed to get out of it. If it’s not then yeah go ahead and use cheaper models with worst quality

I've actually come to believe the overwhelming majority of use cases require nowhere frontier quality so there's that. Much faster execution is just a bonus on top of the much reduced cost
Post reply on HN