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

171–180 of 240 posts

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

#171

Post by try-working »

PhilippGille wrote: post #129
try-working wrote: post #84

Earlier quoted context omitted.

Kimi and GLM models have coined a new term: Thinkslop. They run a chain of thought that is up to 10x longer than other models and it seems that through a lookback mechanism they are able to use the CoT to reason about solutions to tasks they couldn't otherwise solve. The downside is of course that they consume many more tokens off your plan, and also that they are significantly slower. Kimi K2.7 takes about 7x longer…

> Kimi and GLM models have coined a new term: Thinkslop. > [...] > So for now I'm happy with just two models: GPT and DeepSeek. 1. DeepSeek V3.2, V4 Flash, V4 Pro, at high or max thinking, ... when recommending a model it should always be a precise model, not just an AI lab 2. DeepSeek V4 Flash at max thinking is the most verbose model (among top models) in the AA benchmarks. See the "Intelligence Index Token Use" ch…

I said specifically V4 Pro. Flash is not the most verbose, that's more likely to be Kimi.

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

#172

Post by olmo23 »

ramon156 wrote: post #125

I know very little about the current state of replacability of Opus but I do sometimes imagine a reality where Opus has been rebuilt as an open model. What plan does Anthropic have when it does happen? Will they still rent out their own model, will they support the open model and become a resource provider? Will they be able to repay the billions of dollars ? This is probably the first question I would ask someone fr…

> Will they still rent out their own model, will they support the open model and become a resource provider?

Anthropic rents GPUs from xAI to run Claude. If there's an open weights competitor to Opus, why wouldn't Elon host it directly?

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

#173

Post by mark_l_watson »

christophilus wrote: post #47

I've been working with Deepseek V4 Flash (with opencode as the harness). It's been almost indistinguishable from Codex / Claude Code for me. I'm sure I'll run into problems when I get to a stickier ticket to tackle. But so far, it's been quite good, and I find it writes straightforward code. I do think the Chinese models are good enough for an 80/20 rule use case.

I also use DeepSeek v4 flash and v4 pro, but I can’t settle between using Claude Code or OpenCode and it seems like I waste time switching back and forth (especially keeping my personal SKILLs files synced). On one hand, a ton of engineering work has gone into Claude Code, on the other hand all Chinese models I have tried with OpenCode seem well configured out of the box.

I was thrilled to have Gemini Ultra for a month and use as many Opus tokens with AntiGravity as I could use, but I am happier using less capable models like DeepSeek knowing that it is more fun to do more of the work myself, it is a smaller hit on the environment, and incredibly cheaper.

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

#174

Post by RazorBucksICO »

Fr0styMatt88 wrote: post #32
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.…

If we can agree that the AI model is at least as capable as a junior engineer or new contractor, how’s that different to saying “software engineering isn’t worth $200 a month”? Has a very race-to-the-bottom feel to it. Though in the grand scheme of it, $200/mo probably isn’t the real price either. Also looking at it not just in a vacuum - paying for a product that can change what you get from under you doesn’t seem g…

The appropriate price is what the output is worth to you. Some people could pay $10,000/month, some $5 and feel like they were breaking even. There is a big jump between convenience and curiosity uses versus business critical.

OpenAI already charges enterprise users a premium purely for that title over on-demand, no-contract usage. Retail users get a good deal. People make a lot of hay about subsidies but this is a very sane approach if you want exposure to these three different types of customers.

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

#175

Post by mark_l_watson »

59nadir wrote: post #134
timcobb wrote: post #21

Can people share their GLM and open model setups in general please? What provider do you use. Why do you trust it with serving full quality? What harness do you use? Why do you trust it not to have malware (most harnessed are TS apps). I am just trying GLM 5.1 from Nvidia build in open code would love to hear how you all do it, thanks.

> What provider do you use? 1. My own harness + Local (which usually means Qwen3.6-35B-A3B), I use this fairly often for research gathering on topics, info gathering on code bases, etc. 2. My own harness + DeepSeek v4 Flash served by DeepSeek, I added $20 quite some time ago and somehow still have $18.77 in there after I don't know how many prompts. I use this pretty often, slightly less than my local setup, it's gre…

I want to say that I agree with you on the value of writing your own coding harness. I wrote something simple in Emacs Lisp and it makes me happy occasionally using it. I am trying to learn Rust and I am working on my own Rust core orchestration layer and I plan on both a Rust command line client and I already have a Python library wrapper for the Rust code that I have written so far. I write a lot of ‘little books’ and I am almost sure to write yet another one on my current hacking project.

Are my little hacks as effective as OpenCode or Claude Code? No way, but I am learning a lot and having fun.

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

#176

Post by mark_l_watson »

michimagdesign wrote: post #29
timcobb wrote: post #21

Can people share their GLM and open model setups in general please? What provider do you use. Why do you trust it with serving full quality? What harness do you use? Why do you trust it not to have malware (most harnessed are TS apps). I am just trying GLM 5.1 from Nvidia build in open code would love to hear how you all do it, thanks.

Next to my Claude Pro plan, I have subbed to OpenCode Go. I find the OpenCode UX much better than in Claude Code CLI. As for models, I started a few months ago with GLM 5.1 and it was solid and could archive near sonnet-level tasks. It weirdly sputtered out Chinese characters sometimes. Then I switched to Kimi K2.6, which is the Chinese model I used the most until now. It used way too many reasoning tokens (improved…

OpenCode Go looked intriguing and I spent time reading their docs and pricing but didn’t purchase services. Do you think they are running it at a loss to get market share? (Probably not.) I have been happy buying tokens directly from DeepSeek (I am retired and everything I do is open source code and writing open content books (the manuscript files are available along with the source code) so I have no privacy issues). I also use FireWorks.ai to try different models. Both API services are excellent, but I may try OpenCode Go for a month or two to support the devs of OpenCode.

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

#177

Post by vagrantJin »

christophilus wrote: post #47

I've been working with Deepseek V4 Flash (with opencode as the harness). It's been almost indistinguishable from Codex / Claude Code for me. I'm sure I'll run into problems when I get to a stickier ticket to tackle. But so far, it's been quite good, and I find it writes straightforward code. I do think the Chinese models are good enough for an 80/20 rule use case.

That v4 quality is available to everyone in the world for a pittance is beyond remarkable.

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

#178

Post by ipaddr »

ImaCake wrote: post #146
ipaddr wrote: post #112

Earlier quoted context omitted.

For centering divs the free models opencode offers can easily handle that work. DeepSeek V4 Flash is pretty decent.

Sure, but something that is “sonnet tier” is going to get there faster and with less pain. Well worth the 13 cents!

Flash will get their faster then the sonnet tier which involves reasoning which is slow. And you don't need reasoning to center divs.

The sonnet tier sits below claude or chatgpt in terms of price but costs so much more than free models. If you are breaking downtasks now I'm not sure that 13 cents is worth it.

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

#179

Post by trollbridge »

SyneRyder wrote: post #152
kreelman wrote: post #80

Earlier quoted context omitted.

Thanks so much for being bold enough to be fairly open about the costs, how you arrange billing and the advantages that's given you. I've been fooling around with DeepSeek 4 agentically. It's probably not as good as Anthropic offerings, but even those seem to be roiled in politics and strife and DeepSeek 4 is very good IMHO. I'll later try out GLM. I'm in Australia. The government has set up a "return and earn" schem…

> There is probably a market for Deepseek/GLM served from non CCP available servers. I might even look into how hard that would be to setup here. Please do. There is definitely a market for Deepseek / GLM hosted from non-China servers, there's over 20 providers for GLM 5.2 on OpenRouter alone... and they're all either Singapore (home of Z.AI / GLM), China, or US. There is nothing yet listed on OpenRouter from Europe…

Hosting in Australia is not feasible at Australian electricity prices.

(Speaking as a not-so-proud Australian.)

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

#180

Post by trollbridge »

Sanzig wrote: post #169
SyneRyder wrote: post #152

Earlier quoted context omitted.

> There is probably a market for Deepseek/GLM served from non CCP available servers. I might even look into how hard that would be to setup here. Please do. There is definitely a market for Deepseek / GLM hosted from non-China servers, there's over 20 providers for GLM 5.2 on OpenRouter alone... and they're all either Singapore (home of Z.AI / GLM), China, or US. There is nothing yet listed on OpenRouter from Europe…

Same issue in Canada - domestic inference capability for the open models is woefully behind.

Canada has fewer excuses, given sparsely populated places that are cold with nearly infinite water and extremely cheap electricity.
Post reply on HN