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

221–230 of 285 posts

Re: GLM-5.1: Towards Long-Horizon Tasks

#221

Post by XCSme »

BoorishBears wrote: post #184
XCSme wrote: post #126

Earlier quoted context omitted.

General intelligence (not coding) comparison: https://aibenchy.com/compare/z-ai-glm-5-medium/z-ai-glm-5-1-...

Is there really no rule that discourages 99% of your interactions with HN from being peddling some useless slop benchmark?

If it's relevant to the discussion, I hope not.

I've spent probably over100 hours working on this benchmarking/site platform, and all tests are manually written. For me (and many others that reached out to me) are not useless either. I use this myself regularly when choosing and comparing new models. I honestly beleive it is providing value to the conversation.

Let me know if you know of a better platform you can use to compare models, I built this one because I didn't find any with good enough UX.

Re: GLM-5.1: Towards Long-Horizon Tasks

#222

Post by rimliu »

jimmaswell wrote: post #120
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 killer product? Coding assistants and LLM's in general are the single most awe-inspiring achievement of humanity in my lifetime, technological or otherwise. They've already massively improved my and others' lives and they're only going to get better. If pre and post industrial revolution used to be the major binary delineation of our history, I'm fairly confident it will soon be seen as pre and post AI instead.

yeah, painting yourself into a corner at 10x speed is hardly the most awe-inspiring achievement of humanity.

Re: GLM-5.1: Towards Long-Horizon Tasks

#223

Post by orbital-decay »

Ms-J wrote: post #196

Z.ai and their GLM models are pretty low quality. I've been testing it for awhile now since it seemed to have potential as a local model. With this new update it still cannot parse simple, test PDFs correctly. It inconsistently tells me that the value in the name field in the document is incorrect, and has the name reversed to put the last name first. Or that a date is wrong as it's in the past/future, when it is not…

>by the way, which is the best uncensored model at the moment?

There are no such models, depending on your definition of censorship. If you're referring to abliteration and similar automated techniques, they're snake oil.

Re: GLM-5.1: Towards Long-Horizon Tasks

#224

Post by ra »

Ms-J wrote: post #196

Z.ai and their GLM models are pretty low quality. I've been testing it for awhile now since it seemed to have potential as a local model. With this new update it still cannot parse simple, test PDFs correctly. It inconsistently tells me that the value in the name field in the document is incorrect, and has the name reversed to put the last name first. Or that a date is wrong as it's in the past/future, when it is not…

I still use GLM 4.7 for well defined coding tasks. I never got 5.0 to work satisfactorily, it felt like a hosting problem (z.ai) where it would work for a while then, for whatever reason, it couldn't respond to the context any more - but that's just a hunch.

I had no such trouble with 4.7 and find it fast and productive. Haven't tried 5.1; am using openAI models for coding most of the time.

Re: GLM-5.1: Towards Long-Horizon Tasks

#225

Post by DeathArrow »

kay_o wrote: post #34
unicornfinder wrote: post #23

Earlier quoted context omitted.

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.

Is manual compation absolutely mandatory ?

When using GLM 5.1 in Open Code, compaction was done automatically.

Re: GLM-5.1: Towards Long-Horizon Tasks

#227

Post by electroglyph »

rednb wrote: post #202
Ms-J wrote: post #196

Z.ai and their GLM models are pretty low quality. I've been testing it for awhile now since it seemed to have potential as a local model. With this new update it still cannot parse simple, test PDFs correctly. It inconsistently tells me that the value in the name field in the document is incorrect, and has the name reversed to put the last name first. Or that a date is wrong as it's in the past/future, when it is not…

I'e been using their models pretty much daily for the past 2 months to work on the codebase of a very complex B2B2C platform written in an unusual functional language (F#) with an angular frontend. I also use Claude premium daily for another client, and i use Codex. and i can tell you that GLM5 is at this point much more capable than Claude and Codex for complex backend end work, complex feature planning, and long ho…

better than Opus? not even close. after struggling thru server overload for the past couple hours i finally put 5.1 thru the paces and it's....okay. failed some simple stuff that Sonnet/Opus/Gemini didn't. failed it badly and repeatedly actually. this was in typescript, btw. not sure if i'll keep the subscription or not

Re: GLM-5.1: Towards Long-Horizon Tasks

#228

Post by victorbjorklund »

Ms-J wrote: post #196

Z.ai and their GLM models are pretty low quality. I've been testing it for awhile now since it seemed to have potential as a local model. With this new update it still cannot parse simple, test PDFs correctly. It inconsistently tells me that the value in the name field in the document is incorrect, and has the name reversed to put the last name first. Or that a date is wrong as it's in the past/future, when it is not…

I don't agree. I think their models are pretty good. The company's infrastructure though seems to be so so.

Re: GLM-5.1: Towards Long-Horizon Tasks

#229

Post by Glaklloo »

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!)

Google doesn't release Gemma 4 if Gemini is similiar good.

We probably talk abuot a year of progress diffeerence.

Its also still quite expensive for an avg person to consume any of it. Either due to hardware invest, energy cost or API cost.

Also professionally I don't think anyone will really spend a little bit less money of having the 3th quality model running if they can run the best model.

I'm happy that we reach levels were this becomes an alternative if you value open and control though.

Re: GLM-5.1: Towards Long-Horizon Tasks

#230

Post by stavros »

ra wrote: post #224
Ms-J wrote: post #196

Z.ai and their GLM models are pretty low quality. I've been testing it for awhile now since it seemed to have potential as a local model. With this new update it still cannot parse simple, test PDFs correctly. It inconsistently tells me that the value in the name field in the document is incorrect, and has the name reversed to put the last name first. Or that a date is wrong as it's in the past/future, when it is not…

I still use GLM 4.7 for well defined coding tasks. I never got 5.0 to work satisfactorily, it felt like a hosting problem (z.ai) where it would work for a while then, for whatever reason, it couldn't respond to the context any more - but that's just a hunch. I had no such trouble with 4.7 and find it fast and productive. Haven't tried 5.1; am using openAI models for coding most of the time.

I hit this as well. It just seems to hang and process for ages.
Post reply on HN