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

231–240 of 240 posts

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

#231

Post by swiftcoder »

jmalicki wrote: post #228
swiftcoder wrote: post #187

Earlier quoted context omitted.

> The problem is that the differences between flagship and local models are compounding heavily This depends a lot on how you work, and how much of the architectural thinking you do yourself. People seem to lose sight of the fact that a flash model today is as powerful as a frontier model from a year ago. If you were happy with GPT 4.x, you should be ecstatic that equivalent power is now basically free...

I find that with a lot of the cheaper models, I end up spending a lot more time correcting the easy stuff. If I am 100% spot on on the architectural stuff, I have anecdata that some of the frontier models might actually be cheaper than "cheaper" alternatives once you look at what it takes to get to good output, since they require less correction. But that is on pure token costs. When you value the human overseer's ti…

> A model that is 10x more expensive that requires 10% less oversight is just a plain win

I think you are drastically underestimating the cost delta here. We're talking models we can run pretty much continuously for $10/month in tokens.

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

#232

Post by trollbridge »

Sanzig wrote: post #190
trollbridge wrote: post #180

Earlier quoted context omitted.

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

Yep, agreed. Main issue in Canada is a notoriously slow and stingy investment ecosystem. Resource-wise we're incredibly well positioned.

Canadian firms can easily access U.S. capital markets. So the question remains of why we aren’t building all kinds of data centers out in the tundra next to giant hydro plants.

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

#233

Post by jmalicki »

swiftcoder wrote: post #231
jmalicki wrote: post #228

Earlier quoted context omitted.

I find that with a lot of the cheaper models, I end up spending a lot more time correcting the easy stuff. If I am 100% spot on on the architectural stuff, I have anecdata that some of the frontier models might actually be cheaper than "cheaper" alternatives once you look at what it takes to get to good output, since they require less correction. But that is on pure token costs. When you value the human overseer's ti…

> A model that is 10x more expensive that requires 10% less oversight is just a plain win I think you are drastically underestimating the cost delta here. We're talking models we can run pretty much continuously for $10/month in tokens.

For $400/mo I can run multiple continuous sessions of frontier models.

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

#234

Post by devmor »

selcuka wrote: post #224
devmor wrote: post #105

Earlier quoted context omitted.

That doesn’t change value. It’s value whether or not you can maintain a profit over it.

That's the definition of "value" in a broad, economics sense but I don't think it applies to the parent comment of this thread: > I'm not sure how I'm supposed to get $200 of value out of personal use!

If you are not working paycheck to paycheck, but still need to commit that time to work, you may prefer $200 worth of free time that you otherwise could not have - that is my general point of view there.

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

#235

Post by cookiengineer »

cameldrv wrote: post #211
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.…

Yes, but you’re paying with your data unless you’re hosting with a provider you trust or self-hosting.

Kind of funny that you're assuming that you are not paying with your data in both cases.

Do I need to remind you how LLMs are being trained? ...or that Anthropic claimed their codebase is 100% vibecoded, making it uncopyrightable by their own logic? ...or that Anthropic took down all Claude Code leaks they could find using DMCA takedown notices? ...or how do you think the caching mechanisms work when there's allegedly no data stored to be able to cache it?

I'm just saying. Anything you build with online models is their training data anyways. Assuming otherwise is pretty stupid at this point.

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

#236

Post by trollbridge »

forshaper wrote: post #194
Sanzig wrote: post #190

Earlier quoted context omitted.

Yep, agreed. Main issue in Canada is a notoriously slow and stingy investment ecosystem. Resource-wise we're incredibly well positioned.

Would you happen to know why there are so many Canadian investments in American telecom?

Canadian telecom is very obstructionist to outside investment and basically structured around rent seeking for exisiting telecoms.

American telecom lets basically anyone come here and spend money.

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

#237

Post by SyneRyder »

Mossy9 wrote: post #185
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…

Cortecs (EU router) lists GLM 5.2 from Tensorix and Nebius https://cortecs.ai/detailedServerlessView/glm-5.2 So two European providers at least

Thank you, I haven't heard of Cortecs before. Might see if I can integrate this into my harness, or at least wire up Tensorix.

Also, I don't know how accurate that tokens/per/second measure for GLM 5.2 is, but if that is even remotely true, then I won't complain about the mild markup Tensorix have for GLM ;) Thank you for the heads-up!

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

#238

Post by citizenpaul »

rainmaking wrote: post #36
citizenpaul wrote: post #15

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.

Now that's a tremendous pointer, I'm going to have to try that. Do you full on let GLM5 get stuff done on its own or is it more like a guided workflow? The former's what the point releases doubled down on and is also something that uses a lot of juice.

Ive been using openspec and let it do the whole spected out project until its done. I dont interact other than the initial proposal, then apply, archive steps.I often run several in parallel on the same project in opencode.

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

#239

Post by nunodonato »

RugnirViking wrote: post #153
nunodonato wrote: post #132

Earlier quoted context omitted.

it would be a really great option if it didn't lack vision

what do you use vision for? I have failed to find a workflow with it that makes sense, asking it to review screenshots of websites or whatever it misses extremely obvious details like text flowing out of it's container/overlapping other text, things being in entirely the wrong place, etc.

reading pdfs
Post reply on HN