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

91–100 of 285 posts

Re: GLM-5.1: Towards Long-Horizon Tasks

#91

Post by InsideOutSanta »

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.

Re: GLM-5.1: Towards Long-Horizon Tasks

#92

Post by QuantumNomad_ »

adrian_b wrote: post #89
zozbot234 wrote: post #45

Earlier quoted context omitted.

SSD offload is always a possibility with good software support. Of course you might easily object that the model would not be "running" then, more like crawling. Still you'd be able to execute it locally and get it to respond after some time. Meanwhile we're even seeing emerging 'engram' and 'inner-layer embedding parameters' techniques where the possibility of SSD offload is planned for in advance when developing th…

For conversational purposes that may be too slow, but as a coding assistant this should work, especially if many tasks are batched, so that they may progress simultaneously through a single pass over the SSD data.

Three hour coffee break while the LLM prepares scaffolding for the project.

Re: GLM-5.1: Towards Long-Horizon Tasks

#94

Post by epolanski »

johnfn wrote: post #48

GLM-5.0 is the real deal as far as open source models go. In our internal benchmarks it consistently outperforms other open source models, and was on par with things like GPT-5.2. Note that we don't use it for coding - we use it for more fuzzy tasks.

Same thing I noticed.

My use cases are not code editing or authoring related, but when it comes to understanding a codebase and it's docs to help stakeholders write tasks or understand systems it has always outperformed american models at roughly half the price.

Re: GLM-5.1: Towards Long-Horizon Tasks

#95

Post by epolanski »

airstrike wrote: post #29
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.

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

Quality degrades fast with context length for all models.

If you want quality you still have to compact or start new contextes often.

Re: GLM-5.1: Towards Long-Horizon Tasks

#96

Post by zozbot234 »

adrian_b wrote: post #89
zozbot234 wrote: post #45

Earlier quoted context omitted.

SSD offload is always a possibility with good software support. Of course you might easily object that the model would not be "running" then, more like crawling. Still you'd be able to execute it locally and get it to respond after some time. Meanwhile we're even seeing emerging 'engram' and 'inner-layer embedding parameters' techniques where the possibility of SSD offload is planned for in advance when developing th…

For conversational purposes that may be too slow, but as a coding assistant this should work, especially if many tasks are batched, so that they may progress simultaneously through a single pass over the SSD data.

Batching many disparate tasks together is good for compute efficiency, but makes it harder to keep the full KV-cache for each in RAM. You could handle this in an emergency by dumping some of that KV-cache to storage (this is how prompt caching works too, AIUI) and offloading loads for that too, but that adds a lot more overhead compared to just offloading sparsely-used experts, since KV-cache is far more heavily accessed.

Re: GLM-5.1: Towards Long-Horizon Tasks

#97

Post by cmrdporcupine »

benterix wrote: post #31
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.

> Obvious quantization issues Devil's advocate: why shouldn't they do it if OpenAI, Anthropic and Google get away with playing this game?

I think what Anthropic is doing is more subtle. It's less about quantizing and more about depth of thinking. They control it on their end and they're dynamically fiddling with those knobs.

Re: GLM-5.1: Towards Long-Horizon Tasks

#99

Post by ummzokbro »

jauntywundrkind wrote: post #18
bigyabai wrote: post #8

It's an okay model. My biggest issue using GLM 5.1 in OpenCode is that it loses coherency over longer contexts. When you crest 128k tokens, there's a high chance that the model will start spouting gibberish until you compact the history. For short-term bugfixing and tweaks though, it does about what I'd expect from Sonnet for a pretty low price.

Chiming in to second this issue. It is wildly frustrating. I suspect that this isn't the model, but something that z.ai is doing with hosting it. At launch I was related to find glm-5.1 was stable even as the context window filled all the way up (~200k). Where-as glm-5, while it could still talk and think, but had forgotten the finer points of tool use to the point where it was making grevious errors as it went (burn…

This.

GLM5 also had this issue. When it was free on Openrouter / Kilo the model was rock solid though did degrade after 100k tokens gracefully. Same at launch with Zai aside from regular timeouts.

Somewhere around early-mid March zai did something significant to GLM5 - like KV quanting or model quanting or both.

After that it's been russian roulette. Sometimes it works flawlessly but very often (1/4 or 1/5 of the time) thinking tokens spill into main context and if you don't spot it happening it can do real damage - heavily corrupting files, deleting whole directories.

You can see the pain by visiting the zai discord - filled with reports of the issue yet radio silence by zai.

Tellingly despite being open source not a single provider will sell you access to this model at anything approaching the plans zai offers. The numbers just don't work so your choice is either pay per token significantly more and get reliability or put up with the bait and switch.

Re: GLM-5.1: Towards Long-Horizon Tasks

#100

Post by cyanydeez »

QuantumNomad_ wrote: post #92
adrian_b wrote: post #89

Earlier quoted context omitted.

For conversational purposes that may be too slow, but as a coding assistant this should work, especially if many tasks are batched, so that they may progress simultaneously through a single pass over the SSD data.

Three hour coffee break while the LLM prepares scaffolding for the project.

[flagged]
Post reply on HN