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

21–30 of 285 posts

Re: GLM-5.1: Towards Long-Horizon Tasks

#21

Post by verdverm »

wolttam wrote: post #11
embedding-shape wrote: post #9

Earlier quoted context omitted.

> It's an okay model. My biggest issue using GLM 5.1 in OpenCode is that it loses coherency over longer contexts Since the entire purpose, focus and motivation of this model seems to have been "coherency over longer contexts", doesn't that issue makes it not an OK model? It's bad at the thing it's supposed to be good at, no?

long(er) contexts (than the previous model) It does devolve into gibberish at long context (~120k+ tokens by my estimation but I haven't properly measured), but this is still by far the best bang-for-buck value model I have used for coding. It's a fine model

Have you tried gemma4?

I'm curious how the bang for buck ratio works in comparison. My initial tests for coding tasks have been positive and I can run it at home. Bigger models I assume are still better on harder tasks.

Re: GLM-5.1: Towards Long-Horizon Tasks

#23

Post by unicornfinder »

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.

I'm on their pro plan and I respectfully disagree - it's genuinely excellent with GLM 5.1 so long as you remember to /compact once it hits around 100k tokens. At that point it's pretty much broken and entirely unusable, but if you keep context under about 100k it's genuinely on par with Opus for me, and in some ways it's arguably better.

Re: GLM-5.1: Towards Long-Horizon Tasks

#24

Post by margorczynski »

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.

It has been useless for long time when compared to Opus or even something like Kimi. The saving grace was that it was dirt cheap but that doesn't matter if it can't do what I want even after many repeated tries and trying to push it to a correct solution.

Re: GLM-5.1: Towards Long-Horizon Tasks

#25

Post by satvikpendem »

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.

Every model seems that way, going back to even GPT 3 and 4, the company comes out with a very impressive model that then regresses over a few months as the company tries to rein in inference costs through quantization and other methods.

Re: GLM-5.1: Towards Long-Horizon Tasks

#26

Post by wolttam »

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.

This is surprising to me. Maybe because I'm on Pro, and not Lite. I signed up last week and managed to get a ton of good work done with 5.1. I think I did run into the odd quantization quirk, but overall: $30 well spent

Re: GLM-5.1: Towards Long-Horizon Tasks

#27

Post by Mashimo »

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.

I'm also on the lite plan and have been using 5.1 for a few days now. It works fine for me.

But it's all casual side projects.

Edit: I often to /compact at around 100 000 token or switch to a new session. Maybe that is why.

Re: GLM-5.1: Towards Long-Horizon Tasks

#28

Post by ray__ »

dang wrote: post #7
smith7018 wrote: post #6

Earlier quoted context omitted.

Hmm, three spam comments posted within 9 minutes of each other. The accounts were created 15 minutes ago, 51 days ago, and 3 months ago. Interesting. Hopefully these aren't bots created by Z.AI because GLM doesn't need fake engagement.

These comments are probably either by friends of the OP or perhaps associated with the project somehow, which is against HN's rules but not the kind of attack we're mostly concerned with these days. Old-fashioned voting rings and booster comments aren't existential threats and actually bring up somewhat nostalgic feelings at the moment! Thanks for watching out for the quality of HN...

Would love to read a Tell HN post about the kinds of attacks you are concerned with!

Re: GLM-5.1: Towards Long-Horizon Tasks

#29

Post by airstrike »

unicornfinder wrote: post #23
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.

I'm on their pro plan and I respectfully disagree - it's genuinely excellent with GLM 5.1 so long as you remember to /compact once it hits around 100k tokens. At that point it's pretty much broken and entirely unusable, but if you keep context under about 100k it's genuinely on par with Opus for me, and in some ways it's arguably better.

100k tokens it's basically nothing these days. Claude Opus 4.6M with 1M context windows is just a different ball game

Re: GLM-5.1: Towards Long-Horizon Tasks

#30

Post by MegagramEnjoyer »

alex7o wrote: post #20

To be honest I am a bit sad as, glm5.1 is producing mich better typescript than opus or codex imo, but no matter what it does sometimes go into shizo mode at some point over longer contexts. Not always tho I have had multiple session go over 200k and be fine.

Why is that sad? A free and open source model outperforming their closed source counterparts is always a win for the users
Post reply on HN