GLM-5.2 is a step change for open agents

Post by giancarlostoro » Thu, Jun 25, 2026, 1:55 PM UTC

khurs wrote: post #182

giancarlostoro wrote: post #181

Earlier quoted context omitted.

As much as I don't like Mark Zuckerberg, part of me wishes he would get his head in the game and compete with these models, he's literally got all the capability to do so, and he could easily sell the model through deals with GCP, AWS, and Azure. Hell, Amazon needs a hot model they can host that's exclusive to them I feel like, maybe he can work something out with them, whatever the case, it seems so glaringly obviou…

Meta internally have been using Google Gemini "Meta has been using Google’s Gemini large language model for most of its moderation and customer support, but staff have recently been told to switch to Meta’s new foundational model, Muse Spark, the people said." https://www.ft.com/content/39251a31-4a9d-4870-b86c-dc6353d67...

Post by GL26 » Thu, Jun 25, 2026, 2:06 PM UTC

Post by RugnirViking » Thu, Jun 25, 2026, 2:27 PM UTC

bckr wrote: post #192

RugnirViking wrote: post #153

Earlier quoted context omitted.

what do you use vision for? I have failed to find a workflow with it that makes sense, asking it to review screenshots of websites or whatever it misses extremely obvious details like text flowing out of it's container/overlapping other text, things being in entirely the wrong place, etc.

What models have you tried? Gemini 3.1 pro has vision capable of reading my sloppy diaries from 10 years ago, down to small glyphs and doodles.

Post by alpineman » Thu, Jun 25, 2026, 3:12 PM UTC

mrngld wrote: post #170

alpineman wrote: post #162

Earlier quoted context omitted.

Did you read the article? Opus 4.5 has essentially been rebuilt already

Based on DeepSWE, Opus 4.8 gets you more intelligent output at lower price (GLM's token inefficiency is really biting them). GPT5.5 even moreso. And I don't recall about Opus but GPT is much, much faster at getting you the answer (again, GLM's token inefficiency). It's neat, I guess, that we can compare them against models released last year, but I care about my options today, and the pareto frontier is about as far…

Post by chess10kp » Thu, Jun 25, 2026, 3:29 PM UTC

timcobb wrote: post #21

Can people share their GLM and open model setups in general please? What provider do you use. Why do you trust it with serving full quality? What harness do you use? Why do you trust it not to have malware (most harnessed are TS apps). I am just trying GLM 5.1 from Nvidia build in open code would love to hear how you all do it, thanks.