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

GLM 5.2 vs. Opus

techstackups.com

Post reply on HN
Print view View original

301–310 of 367 posts

Re: GLM 5.2 vs. Opus

#301

Post by ethanpil »

esperent wrote: post #179
thunspa wrote: post #167

Earlier quoted context omitted.

Care to share more about your pi setup? I've recently started using it (after long-time Claude Code work) and was wondering how you'd achieve these long-running tasks. Do you allow it to spawn sub-agents? Thank you!

My pi usage over the past ~5 months went roughly like this: * Install pi and a bunch of extensions from their package repo * Realize that all the packages (with a few exceptions) are massively overcomplicated and vibe coded * Ask pi to rebuild a very simple version of the packages I used. So e.g. subagents - all the default subagent extensions are massively complicated with named agents, recursion, communication. I m…

I'd like to study your setup. Would you be willing to share? Perhaps a github repo of your 5 extensions or even a pastebin if you would be so inclined. I would be grateful to learn more about this by studying from your success...

Re: GLM 5.2 vs. Opus

#302

Post by g42gregory »

The quality that matters a lot to me is what I call "Helpfulness". An art of being helpful. While GPT came a long way from "you are wrong and I can prove it to you", Claude wins hands down in terms of "being helpful". If task is underspecified or has wrong elements, it will try to correct the best it can.

I read that GLM 5.2 (and other GLM models) were specifically trained to be "helpful" as Claude is. I have big hopes on GLM line of models growing to be a real alternative to the Claude in the near future.

Re: GLM 5.2 vs. Opus

#303

Post by hmokiguess »

w4yai wrote: post #207
hmokiguess wrote: post #169

I signed up for GLM 5.2 yesterday to try it out because Anthropic kept throwing 529 Overloaded I like it, but the lite plan ate 22% usage of my 5h reset window in a single session after 2 prompts on xhigh of GLM 5.2 [1m] Result was satisfactory, I think stuff is decent, I'm happy to use either, wish there was a combined subscription plan where I could get both

I may be biased and interested as I'm going to give you an affiliate link, but really honestly Synthetic LLM provider is a beast! They provide perfect GLM5.2, awesome token/s, TTFT and price. Coupled with a local Headroom ( https://github.com/headroomlabs-ai/headroom ) you'll be able to use a LOT without hitting your 5h window :) Definitely the best $ value for me considering the reasonable performance of GLM5.2. The…

how do I configure claude code / pi with it? sounds like a good deal!

EDIT: I've RTFM lol, thanks for the links, will give it a shot!

Re: GLM 5.2 vs. Opus

#304

Post by mellosouls »

InsideOutSanta wrote: post #271
mellosouls wrote: post #264

GLM-5.2 cost a fraction as much. Opus finished in half the time and shipped a cleaner game This implies Opus was potentially much (?) better value. GLM cost a quarter but Opus was twice as fast. So we are already at GLM actually costing half when you compare on time, without even considering the extra effort and time it would take to get Opus-par results. It's good to have cheaper options and very impressive to see t…

For me, time doesn't matter for LLMs. I can start a bunch of tasks, and I'll review the PRs when they're done. Faster is nicer, but if the task gets done correctly, I'm good.

Me too, I just think the comparison was a bit simplistic, at least in the expression of it.

Re: GLM 5.2 vs. Opus

#305

Post by w4yai »

hmokiguess wrote: post #303
w4yai wrote: post #207

Earlier quoted context omitted.

I may be biased and interested as I'm going to give you an affiliate link, but really honestly Synthetic LLM provider is a beast! They provide perfect GLM5.2, awesome token/s, TTFT and price. Coupled with a local Headroom ( https://github.com/headroomlabs-ai/headroom ) you'll be able to use a LOT without hitting your 5h window :) Definitely the best $ value for me considering the reasonable performance of GLM5.2. The…

how do I configure claude code / pi with it? sounds like a good deal! EDIT: I've RTFM lol, thanks for the links, will give it a shot!

The docs are really helpful : https://dev.synthetic.new/docs/guides/claude-code

Glad you figured it out :) Let me know your thoughts about the quota and GLM5.2, so far I don't think I've came across against anything better, $/usefulness wise.

Re: GLM 5.2 vs. Opus

#306

Post by lukaslalinsky »

Terretta wrote: post #244
lukaslalinsky wrote: post #225

I was never able to get these models to collaborate with me the way Opus does. I'm probably an outliner, I don't one-shot projects, I don't vibe code. I basically use LLMs are if I was working with a coworker, fairly smart one, but with short memory and often missing the big picture. Sometimes I can delegate more, sometimes less, but I know I always have to stay on top of what's happening, because it WILL create mess…

> Opus 4.6 which was bad for some reason If I recall, that model had a couple issues. One was the issue of being monkeyed with, for which they gave everyone credits. The other feature/bug, depending on your POV, was being Anthropic's least personable release, not papering over everything with self help guru therapy language. Opus 4.6 didn't LARP. It was more direct, less fussy, less discussy, and very much less "wait…

I considered Opus 4.5 to be the peak for a while. Opus 4.6 tended to over think, and generally get lost in thinking. I asked something and Claude Code would just spin for 15 minutes. And it was not the harness, if I changed the model to 4.5, it was fine again. So I skipped the following releases. I've been working with Opus 4.8 the last weeks and while I don't like how talkative it is, but it is fine to work with interactively. I've also used Fable for the few days it was available, and indeed, that was model worth using for my use case. To the point, but still very interactive.

Re: GLM 5.2 vs. Opus

#307

Post by drob518 »

thewebguyd wrote: post #263
OtomotO wrote: post #94

Earlier quoted context omitted.

I think that LLMs will stay, but I also think we've plateaued and that big companies will fail and fall and we will have another years long "halt" of any real advancements coming to the public. Similar to how ML was all the hype about 12 years ago and then it submerged again for a couple of years.

> we will have another years long "halt" of any real advancements coming to the public One can hope. Probably an unpopular take here but I'm tired boss. The software world has a huge backlog of things that can all be done with the tech we currently have, no breakthrough advancements needed, but none of it will get prioritized when we're all forced to run on the new and shiny treadmill. Ever since LLM hype its like th…

Yep, I see it.

Re: GLM 5.2 vs. Opus

#308

Post by xlii »

nijave wrote: post #250
xlii wrote: post #6

I've been checking out GLM 5.2 on some projects and few thoughts on it: - it takes it sweet time to get code rolling, not the fastest model by any means - it strays a lot during discovery/planning but then corrects - it's not steering friendly, as it hallucinates things that it doesn't follow later on - its output is quite good A sample use case: I was optimizing rendering on Swift+Zig codebase. It chocked on 5k data…

>it takes it sweet time to get code rolling, not the fastest model by any means Which provider are you using? I got a z.ai Lite Coding Plan and it's my understanding z.ai is on the slower side of providers and the Lite plan gets lower priority on top of that. In the api key console, it shows dipping below 60 tok/sec which is quite slow.

I have Max access from a friend. It's not about token generation but time-to-first-edit. It tends to think 3-10 minutes before that.

Re: GLM 5.2 vs. Opus

#309

Post by lukaslalinsky »

x312 wrote: post #258
lukaslalinsky wrote: post #225

I was never able to get these models to collaborate with me the way Opus does. I'm probably an outliner, I don't one-shot projects, I don't vibe code. I basically use LLMs are if I was working with a coworker, fairly smart one, but with short memory and often missing the big picture. Sometimes I can delegate more, sometimes less, but I know I always have to stay on top of what's happening, because it WILL create mess…

A lot of open weight models don't understand intent well, they'll overfixate on a word in the prompt or just go off the rails trying to do much work. GLM-5.2 actually has really good intent understanding though, on par with GPT-5.5 and Opus from my experience.

I'll have to try it. I was using earlier GLM models, incluing 5.1, and was always disappointed.

Re: GLM 5.2 vs. Opus

#310

Post by 0xbadcafebee »

Flaws in this test setup:

  - A zero-shot prompt, run once (in total)
  - No planning run (which improves output)
  - Different coding harnesses & system prompts
  - Unknown provider for GLM (there are 15 different GLM-5.2 providers with varying quality & latency)
  - No documentation of thinking effort level
  - No vision model supplement (you can provide a subagent w/a vision model)
You can't take this comparison seriously. There were many different variables, no control, no repeat test. It's as useful a comparison as picking a random tweet with both models' names
Post reply on HN