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

GLM-5.1: Towards Long-Horizon Tasks

z.ai

Post reply on HN
Print view View original

171–180 of 285 posts

Re: GLM-5.1: Towards Long-Horizon Tasks

#171

Post by AlienRobot »

grafmax wrote: post #140
dvt wrote: post #118

Every single day, three things are becoming more and more clear: (1) OpenAI & Anthropic are absolutely cooked; it's obvious they have no moat (2) Local/private inference is the future of AI (3) There's *still* no killer product yet (so get to work!)

> no moat I'd like to think the superior product wins. But Windows still thrives despite widespread Linux availability. I think sometimes we can underestimate the resilience of the tech oligopolies, particularly when they're VC-funded.

>I'd like to think the superior product wins. But Windows still thrives despite widespread Linux availability.

That's because by most metrics Linux is inferior is Windows.

Re: GLM-5.1: Towards Long-Horizon Tasks

#172

Post by marcus_holmes »

kcb wrote: post #170
marcus_holmes wrote: post #166

Earlier quoted context omitted.

Well, there kinda was - most computing then was done on mainframes. Personal / Micro computers were seen as a hobby or toy that didn't need any "serious" amounts of memory. And then they ate the world and mainframes became sidelined into a specific niche only used by large institutions because legacy. I can totally see the same happening here; on-device LLMs are a toy, and then they eat the world and everyone has the…

The difference is computers post text terminal are latency and throughput dependent to the user. LLMs are not particularly.

Sorry, I don't understand that comment. Can you clarify, please?

Re: GLM-5.1: Towards Long-Horizon Tasks

#173

Post by svcrunch »

bottlepalm wrote: post #168
dvt wrote: post #118

Every single day, three things are becoming more and more clear: (1) OpenAI & Anthropic are absolutely cooked; it's obvious they have no moat (2) Local/private inference is the future of AI (3) There's *still* no killer product yet (so get to work!)

This has got to be bait.. 1) OpenAI and Anthropic are killing it, and continue to do so, their coding tools are unmatched for professionals. 2) Local models don't hold a candle to SOTA models and there's nothing on the horizon that indicates that consumers will be able to run anything close to what you can get in a data center. 3) Coding is a killer product, OpenAI and Anthropic are raking in the cash. The top 3 apps…

The grandparent is definitely wrong on (3). Yes, coding is a killer product, I agree with you.

On (2), I agree with you for local models. BUT, there are also the open source Chinese models accessible via open-router. Your argument ("don't hold a candle to SOTA models") does not hold if the comparison is between those.

On (1), I agree more with the grandparent than with your assessment. Yes, OpenAI and Anthropic are killing it for now, but the time horizon is very short. I use codex and claude daily, but it's also clear to me that open source is catching up quickly, both w.r.t. the models and the agentic harnesses.

Re: GLM-5.1: Towards Long-Horizon Tasks

#174

Post by kcb »

marcus_holmes wrote: post #172
kcb wrote: post #170

Earlier quoted context omitted.

The difference is computers post text terminal are latency and throughput dependent to the user. LLMs are not particularly.

Sorry, I don't understand that comment. Can you clarify, please?

My point is LLMs aren't more usable if the hardware is in your room versus a few states away. Personal computers still to this day aren't great when the hardware is fully remote.

Re: GLM-5.1: Towards Long-Horizon Tasks

#175

Post by kcb »

CamperBob2 wrote: post #146
kcb wrote: post #119

Earlier quoted context omitted.

What benefit is there to dropping $50k on GPUs to run this personally besides being a cool enthusiast project?

It will run exactly the same tomorrow, and the next day, and the day after that, and 10 years from now. It will be just as smart as the day you downloaded the weights. It won't stop working, exhaust your token quota, or get any worse. That's a valuable guarantee. So valuable, in fact, that you won't get it from Anthropic, OpenAI, or Google at any price.

That's why we all still use our e machines its never obsolete PCs. Works just the same it did 20 years ago, though probably not because I've never heard of hardware that's guaranteed not to fail.

Re: GLM-5.1: Towards Long-Horizon Tasks

#176

Post by fwipsy »

kcb wrote: post #154
fwipsy wrote: post #151

Earlier quoted context omitted.

Agree directionally but you don't need $50k. $5k is plenty, $2-3k arguably the sweet spot.

The 4-bit quants are 350GB, what hardware are you talking about?

qwen3:0.6b is 523mb, what model are you talking about? You seem to have a specific one in mind but the parent comment doesn't mention any.

For a hobby/enthusiast product, and even for some useful local tasks, MoE models run fine on gaming PCs or even older midrange PCs. For dedicated AI hardware I was thinking of Strix Halo - with 128gb is currently $2-3k. None of this will replace a Claude subscription.

Re: GLM-5.1: Towards Long-Horizon Tasks

#177

Post by itake »

svcrunch wrote: post #173
bottlepalm wrote: post #168

Earlier quoted context omitted.

This has got to be bait.. 1) OpenAI and Anthropic are killing it, and continue to do so, their coding tools are unmatched for professionals. 2) Local models don't hold a candle to SOTA models and there's nothing on the horizon that indicates that consumers will be able to run anything close to what you can get in a data center. 3) Coding is a killer product, OpenAI and Anthropic are raking in the cash. The top 3 apps…

The grandparent is definitely wrong on (3). Yes, coding is a killer product, I agree with you. On (2), I agree with you for local models. BUT , there are also the open source Chinese models accessible via open-router. Your argument ("don't hold a candle to SOTA models") does not hold if the comparison is between those. On (1), I agree more with the grandparent than with your assessment. Yes, OpenAI and Anthropic are…

> the open source Chinese models accessible via open-router

And? They aren't as good as SOTA models. Even the SOTA model provider's small models aren't worth using for many of my coding tasks.

Re: GLM-5.1: Towards Long-Horizon Tasks

#178

Post by kay_o »

InsideOutSanta wrote: post #91
RickHull wrote: post #14

I am on their "Coding Lite" plan, which I got a lot of use out of for a few months, but it has been seriously gimped now. Obvious quantization issues, going in circles, flipping from X to !X, injecting chinese characters. It is useless now for any serious coding work.

My impression is that different users get vastly different service, possibly based on location. I live in Western Europe, and it works perfectly for me. Never had a single timeout or noticeable quality degradation. My brother lives in East Asia, and it's unusable for him. Some days, it just literally does not work, no API calls are successful. Other days, it's slow or seems dumber than it should be.

It's now mid weekday in China timezone.

Starting an hour or two ago GLM's API endpoint is failing 7/8 times for me, my editor is retrying every request with backoff over a dozen times before it succeeds and wildly simple changes are taking over 30 minutes per step.

Re: GLM-5.1: Towards Long-Horizon Tasks

#179

Post by gertlabs »

We're still adding samples, but some early takeaways from benchmarking on https://gertlabs.com:

Contrary to the model card, its one-shot performance is more impressive than its agentic abilities. On both metrics, GLM 5.1 is competitive with frontier models.

But keeping in mind this is an open source model operating near the frontier, it's nothing short of incredible.

I suspect 2 issues with the model are keeping it from fully realizing its potential in agentic harnesses: - Context rot (already a common complaint). We are still working on a metric to robustly test and visualize this on the site. - The model was most likely overtrained on standardized toolsets and benchmarks, and isn't as adaptive in using arbitrary tooling in our custom harness simulations. We've decided to commit to measuring intelligence as the ability to use custom, changing tools, instead of being trained to use specific tools (while still always providing a way to run local bash and other common tools). There are arguments to be made for either, but the former is more indicative of general intelligence. Regardless, it's a subtle difference and GLM 5.1 still performs well with tooling in our environments.

Crazy week for open source AI. Gemma 4 has shown that large model density is nowhere near optimized. Moats are shrinking.

If there are more representations of model performance you'd like to see, I'm actively reading your feedback and ideas.

Re: GLM-5.1: Towards Long-Horizon Tasks

#180

Post by fwipsy »

unlikelytomato wrote: post #153
fwipsy wrote: post #151

Earlier quoted context omitted.

Agree directionally but you don't need $50k. $5k is plenty, $2-3k arguably the sweet spot.

as a local LLM novice, do you have any recommended reading to bootstrap me on selecting hardware? It has been quite confusing bring a latecomer to this game. Googling yields me a lot of outdated info.

First answer: If you haven't, give it a shot on whatever you already have. MoE models like Qwen3 and GPT-OSS are good on low-end hardware. My RTX 4060 can run qwen3:30b at a comfortable reading pace even though 2/3 of it spills over into system RAM. Even on an 8-year-old tiny PC with 32gb it's still usable.

Second answer: ask an AI, but prices have risen dramatically since their training cutoff, so be sure to get them to check current prices.

Third answer: I'm not an expert by a long shot, but I like building my own PCs. If I were to upgrade, I would buy one of these:

Framework desktop with 128gb for $3k or mainboard-only for $2700 (could just swap it into my gaming PC.) Or any other Strix Halo (ryzen AI 385 and above) mini PC with 64/96/128gb; more is better of course. Most integrated GPUs are constrained by memory bandwidth. Strix Halo has a wider memory bus and so it's a good way to get lots of high-bandwidth shared system/video RAM for relatively cheap. 380=40%; 385=80%; 395=100% GPU power.

I was also considering doing a much hackier build with 2x Tesla P100s (16gb HBM2 each for about $90 each) in a precision 5820 (cheap with lots of space and power for GPUs.) Total about $500 for 32gb HBM2+32gb system RAM but it's all 10-year-old used parts, need to DIY fan setup for the GPUs, and software support is very spotty. Definitely a tinker project; here there be dragons.

Post reply on HN