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

221–230 of 240 posts

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

#221

Post by andriy_koval »

wuhhh wrote: post #18
jauntywundrkind wrote: post #14

Earlier quoted context omitted.

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…

> Coming from Claude, I was just not used to seeing this

Claude doesn't show its internal Cot?

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

#222

Post by sixothree »

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.

My first instinct has been - well this is an open source project, what does it matter. But even then, I am guessing that using their service even for open source projects still provides them some value.

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

#223

Post by fbrncci »

lanthissa wrote: post #137
fbrncci wrote: post #62

Earlier quoted context omitted.

You made me realize something. I routinely spend upwards of 500$ per month on LLMs for coding (expensed towards clients). However I live in a place where 500$ is around the avg. salary. I’m lucky that I know my way around western clients. Clients who pay these expenses and are happy to work with me because I am still about 50% cheaper than local talent in EU/US, while my salary at home converts to an upper class inco…

AI is the first technology that doesn't incentivize offshoring, and incentivizes co-location of talent. A NYC dev and a dev in india have the same ai costs, based the ratio tokens/salary it becomes less of comparative disadvantage to be in NYC. Now combine that with the fact that AI makes the act of generating code less a % time of the job, and the ability to get/refine requirements more of the job and you have a dec…

The tokens/salary ratio is not relevant at all. Because while 200-500$ is a lot of money, it’s still a fraction of the salary you’d pay any dev in the world. It just comes out as a tooling expense. It also matters how those devs use the tools; you can’t assume everyone gets the same out of it. So that amount can last a day or it can last a month. I would say a dev in a developing nation would be more budget aware than someone being used to everything being priced in NYC rates.

For example I build other AI products and I have been hyper aware of the token spend of our users. I was going crazy seeing that some users were having 5$ conversations. So that was optimized and I found ways to use sub agents to get it down to 1-2$. Just for management asking me why I was worrying to begin with? The users using these are consultants being paid 120$ per hour. They have a daily 10-20$ token expense, no problem. “But amazing job on the cost reduction.”.. well 5$ for me is what I spend on food daily. While the consultant is slamming: “yes” 10 times in a chat , for whatever reason for the same cost. Would the NYC dev care as much natively? No.

You can still hire three devs in India for the price of a dev in NYC. Now you give them AI and you might only need 1-2. That makes offshoring even more appealing, not less. And the dev in India now having tooling to out compete local talent. Well that’s my reality (I am not in India though).

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

#224

Post by selcuka »

devmor wrote: post #105
selcuka wrote: post #70

Earlier quoted context omitted.

Obviously this assumes that you can find 4+ extra hours of $50/hr work every month, or you can work 4 hours less. Neither of these assumptions is correct for people who work for a fixed salary.

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!

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

#225

Post by selcuka »

holoduke wrote: post #124
Kuxe wrote: post #122

Earlier quoted context omitted.

In Sweden $200 is ~5% of average programmer monthly income after tax. $200/h rate is not a representative salary for SEs in South America, Asian countries nor Europe. If you're running a business I agree it's a no-brainer, but the context here is for personal projects.

Come on. The 200 spend on Claude is easily earned back. A few hours of work maximum.

According to your parent comment, even in Sweden, it's 8.7 hours of work, more than a full day.

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

#226

Post by ttoinou »

matheusmoreira wrote: post #217
ttoinou wrote: post #196

Earlier quoted context omitted.

How about brazilian median software developer wage ?

According to Glassdoor statistics, brazilian developers make between 600-1600 USD per month on average. Seniors might rise above 2000 USD. So a 200 USD subscription falls between 10% and 33% of an average brazilian developer's salary.

So it’s 10x to 3x cheaper…

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

#227

Post by HappMacDonald »

rglullis wrote: post #139
arikrahman wrote: post #40

Earlier quoted context omitted.

Someone else on this forum put it well, U.S. is trying to achieve AGI at all costs, while Chinese models are seeking widespread adoption.

> U.S. is trying to achieve AGI at all costs If that was true, they would be collaborating with each other and opening up all the results from their work.

.. "NOBUS" AGI with a moat at all costs..

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

#228

Post by jmalicki »

swiftcoder wrote: post #187
whazor wrote: post #165

Earlier quoted context omitted.

The problem is that the differences between flagship and local models are compounding heavily. An 4% different could be massive when you keep iterating on the same code base.

> 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 time, there is just no competition. A model that is 10x more expensive that requires 10% less oversight is just a plain win.

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

#229

Post by redmalang »

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.

We have switched approx 80% of our work to deepseek, and it works great. Our setup is a bit unconventional though, we upload all cot / sessions to shared storage and generate centralised project level context. We've found this is helpful in directing and working with these slightly less sota models and getting great value for ai spend.

I'm planning to open source all this infra soon, hopefully useful for others too.

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

#230

Post by adrian_b »

GL26 wrote: post #193

if someone has any tutorial on how to run GLM-5.2 from a Rasberry Pi 5 (AI hat), I want it !

The full GLM-5.2 has 1.4 terabytes of data.

Even in quantized form, reducing that size by 2 times or 4 times, a Raspberry Pi 5 could not run it otherwise than by reading the weights from an SSD.

Even thus, I do not believe that a Raspberry Pi 5 would be fast enough to be able to run inference on such a big model at the speed at which it can read from the SSD.

On the other hand, there are many mini-PCs with Intel or AMD CPUs that have both a PCIe 5.0 SSD and a PCIe 4.0 SSD, which may be read in parallel, achieving thus a reading throughput of up to 20 Gbyte/s.

Such miniPCs have fast enough CPUs/GPUs, so that they might be able to reach the inference speed limited by a 20 Gbyte/s weight reading throughput, which for a so big model like GLM-5.2 would be of one output token every few seconds (only a fraction of the weights must be read for one output token). The ratio between output tokens per second and the weight reading throughput can be improved by various methods, like multi-token prediction or batching multiple tasks.

Optimizing inference speed in such conditions is an active research subject, due to the high current memory prices.

Post reply on HN