finnjohnsen2

Most people live in "other countries". Like the whole of Europe. And we have been doing just fine. Many of us have worked in tech this whole time too. It's gonna be fine even if you dont live in the leader country (anymore).

> "good for the world" because... what, they offer this service cheaply? lol

cheaply is nice, but the main point is that GLM is open weights. A resounding YES: z.ai are doing the good for the world.

I switched to GLM on 5.2 and I am happy to be off the two evil frontier providers.

But now I have two new issues:

1. I have fomo from not being face-in the bleeding edge of things.

2. I am ambivalent about z.ai. China -based company is problematic, but they should get my money since they do good for the world. Switching to Mistral for GLM makes my problem inverse since the money doesnt go exactly to to the right place but I trust a french company.

Lets hope the near future resolves our need for personal VRAM and ultimately full self hosting. Coding must be free again. This is the way.

So your planner leaves markdown files I assume...?

Do you switch model mid session, or do you use subagent to do the switch after planning?

Is Grok relevant? Who uses it?

Maybe I'm in some kind of bouble but I have never met or talked to anyone who has used Grok.

yes, but it uses 17gb VRAM when running a 50 inference steps generation from prompt. Which is more than I expected since a 7B model sounds little.

I use opencode + <a decent saas llm> to set up all this new ai generation stuff. GLM-5.3 is my current gun. Safely inside podman containers too because I dont trust this fast moving python eco system at all. Never do I want this running on my main OS.

I have FLUX.2 klein and dev, Ideogram, LaDA-Image and SenseNova locally. Works great. Ive never touched a file.

The days of making container yamls myself is over. I read them but I dont edit anymore.

I would call this a license trap: Qwen RESEARCH LICENSE AGREEMENT

Code on github, models on huggingface, nice intro text: "We are excited to open-source Qwen-Image-2.1 [...]".

meh...

So one model is "Not used to improve our products" and is 10-20 times more expensive to the "Used to improve our products"-model.

Given this is Meta, my immediate assumptions that one is cheap because it lets me "be the product". I know I'm rushing to conclusions but there is zero trust here. The brain will do its thing. And the wording here is giving the brains a lot of wiggle room.

OpenCode+GLM-5.3 (and 5.2) for three weeks solid. Im so happy I made it out

We don't trust you Zuck but we'll take it. Thanks.

no ACP support it seems :( Of all the AI buzzwords I love ACP because of the separation of concern. Let the editor be an editor, the harness be the ai code agent, and the llm be the llm