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

GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

z.ai

Post reply on HN
Print view View original

481–490 of 540 posts

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#481

Post by astrod »

girvo wrote: post #460
sheepscreek wrote: post #430

Earlier quoted context omitted.

I bought the Gemini Ultra to try for a month (at the discounted price). I have been using it non-stop for Opus 4.6 Thinking, which is much better than Gemini 3 Pro (High) and it's been a blast. The most I've managed to consume is 60% of my 5 hourly quota. That was with 2-3 instances in parallel. I hope too many of us won't be doing this and cause Google to add limits! My hope is Google sees the benefit in this and go…

How do you use Opus through Gemini Ultra? I must be missing something

It's available in antigravity.

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#482

Post by ben_w »

MrsPeaches wrote: post #475
hasperdi wrote: post #469

Earlier quoted context omitted.

That's a bike that's ergonomically designed for pelicans. It is unreasonable to expect pelicans to ride human bikes, they have different anatomy.

The next frontier: Draw a pelican on a bicycle ergonomically designed for pelicans.

It may be a joke, but I think this is correct.

For reasons, I have tried to get Stable Diffusion to put parrots into spacesuits. Always ended up with the beak coming out where the visor glass should've been, either no wings at all or wings outside the suit, legs and torso just human-shaped.

ChatGPT got the helmet right, but their wings and tail (and sometimes claws) were exposed to vacuum, still very much closer to a human in either a normal or scifi space suit that happens to also be wearing a parrot head inside the space suit, and has tacked some costume wings on the outside.

Essentially, it's got the same category of wrong as fantasy art's approach to what women's armour should look like: aesthetics are great, but it would be instantly lethal if done for real.

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#483

Post by lostmsu »

xupybd wrote: post #381

I've been using GLM 4.7 with opencode. It is for sure not as good but the generous limits mean that for a price I can afford I can use it all day and that is game changer for me. I can't use this model yet as they are slowly rolling it out but I'm excited to try it.

Have you compared it to GPT? It is a much better model, and unlike Claude you won't easily hit limits on Pro plan.

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#484

Post by 9dev »

l_eo wrote: post #326
btown wrote: post #227

Earlier quoted context omitted.

Thank you for continuing to maintain the only benchmarking system that matters! Context for the unaware: https://simonwillison.net/tags/pelican-riding-a-bicycle/

They will start to max this benchmark as well at some point.

Simon has written a page specifically for you: https://simonwillison.net/2025/nov/13/training-for-pelicans-...

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#485

Post by 9cb14c1ec0 »

It feels like Anthropic's models from 6 months ago. I mean, it's great progress in the open weight world, but I don't have time to use anything less than the very best for the coding I do. At the same time, if Anthropic and OpenAI disappeared tomorrow, I could survive with GLM-5.

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#486

Post by nake89 »

2001zhaozhao wrote: post #312

GLM-4.7-Flash was the first local coding model that I felt was intelligent enough to be useful. It feels something like Claude 4.5 Haiku at a parameter size where other coding models are still getting into loops and making bewilderingly stupid tool calls. It also has very clear reasoning traces that feel like Claude, which does result in the ability to inspect its reasoning to figure out why it made certain decisions…

Slightly off topic. I had a hard time getting models to run with ollama, and I thought that my computer (32gm ram, GTX4070 12Gb vram) just couldn't do it. The I tried LM Studio and after fiddling with some settings, I got models running and quite fast. I didn't try GLM-4.7 flash but I did GLM-4.6v flash and it was amazing to see it be able to analyze all kinds of images (since it has vision support). I was simply stunned. I can't believe that a simple gaming machine can do many of the things I used cloud models for. It was absolutely strikingly good at guessing locations of photos. Even vague ones. Deducing landmarks, writings, types of traffic signs. I need to try 4.7 flash. Hopefully it can ran fast with my machine.

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#488

Post by apples_oranges »

9cb14c1ec0 wrote: post #485

It feels like Anthropic's models from 6 months ago. I mean, it's great progress in the open weight world, but I don't have time to use anything less than the very best for the coding I do. At the same time, if Anthropic and OpenAI disappeared tomorrow, I could survive with GLM-5.

How is the very best right now? Smooth sailing or still frustrating at times?

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#489

Post by lossolo »

lostmsu wrote: post #479
sschueller wrote: post #436

Earlier quoted context omitted.

Funny, living in Europe, I prefer using EU and Chinese hosts because as I don't want my data going to the US. The trust in US firms and state is completely gone.

Tangent note: this sounds like the same mistake as EU's reliance on Russia.

Not really. China doesn't share a border with us, doesn't claim any EU territory, and didn't historically rule our lands the way the USSR did. In the context of spheres of influence and security interests, its strategic goals aren't directly at odds with the EU's core interests.

Re: GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

#490

Post by machiaweliczny »

apples_oranges wrote: post #488
9cb14c1ec0 wrote: post #485

It feels like Anthropic's models from 6 months ago. I mean, it's great progress in the open weight world, but I don't have time to use anything less than the very best for the coding I do. At the same time, if Anthropic and OpenAI disappeared tomorrow, I could survive with GLM-5.

How is the very best right now? Smooth sailing or still frustrating at times?

Claude: you get rate-limited with one prompt so hard to validate 4.6

Codex: better with rate-limits, 5.2 strong with logic problems

Cursor: cursor auto - a bit dumb still but I use the most for writing not really thinking, it's also good at searching through codebase and doing summaries etc.

Claude / Codex still miss tons of scaffolding for sane development or it's due to sandboxes or sth. Like for example you ask in /plan mode to check think with link to github and it does navigate github via curl, hitting rate limits etc. instead of just git clone, repomix etc. so scaffolding still matters a lot. Like it still lacks a tons of common sense

Post reply on HN