Hacker News: finnjohnsen2

New comment by finnjohnsen2 in "Anthropic blocks users for anything touching training larger models"

finnjohnsen2 — Sun, 01 Nov 2026 08:23:00 +0000

Open Weight MUST be our common future

New comment by finnjohnsen2 in "China Overtakes U.S. For First Time as Top Spender on R&D in 2024"

finnjohnsen2 — Tue, 13 Oct 2026 12:37:06 +0000

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).

New comment by finnjohnsen2 in "Just say no to OpenAI and Anthropic"

finnjohnsen2 — Mon, 12 Oct 2026 18:52:25 +0000

> "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.

New comment by finnjohnsen2 in "Just say no to OpenAI and Anthropic"

finnjohnsen2 — Mon, 12 Oct 2026 18:39:59 +0000

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.

New comment by finnjohnsen2 in "One month coding with GLM 5.3 Flash"

finnjohnsen2 — Sat, 03 Oct 2026 14:10:56 +0000

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

New comment by finnjohnsen2 in "One month coding with GLM 5.3 Flash"

finnjohnsen2 — Fri, 02 Oct 2026 21:57:50 +0000

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

New comment by finnjohnsen2 in "Grok 4.7"

finnjohnsen2 — Mon, 21 Sep 2026 20:25:31 +0000

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.

New comment by finnjohnsen2 in "Qwen Image 2.1"

finnjohnsen2 — Mon, 21 Sep 2026 11:42:03 +0000

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.

New comment by finnjohnsen2 in "Qwen Image 2.1"

finnjohnsen2 — Sun, 20 Sep 2026 18:34:59 +0000

I use opencode + 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.

New comment by finnjohnsen2 in "Qwen-Image-2.1: Compact, efficient, and unified image creation"

finnjohnsen2 — Sun, 20 Sep 2026 18:18:03 +0000

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...

New comment by finnjohnsen2 in "Muse Spark 1.3"

finnjohnsen2 — Wed, 02 Sep 2026 19:52:02 +0000

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.

New comment by finnjohnsen2 in "Claude Fable 5.1 and Claude Mythos 5.1"

finnjohnsen2 — Tue, 01 Sep 2026 21:19:01 +0000

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

New comment by finnjohnsen2 in "Mark Zuckerberg attacks 'closed' AI rivals as Meta returns to open models"

finnjohnsen2 — Tue, 11 Aug 2026 13:25:16 +0000

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

New comment by finnjohnsen2 in "ZCode – Harness for GLM-5.2"

finnjohnsen2 — Thu, 02 Jul 2026 13:30:02 +0000

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

New comment by finnjohnsen2 in "U.S. government will decide who gets to use GPT-5.6"

finnjohnsen2 — Fri, 26 Jun 2026 21:11:26 +0000

Less money to US AI tech. This could be good long term to move us away from them.

New comment by finnjohnsen2 in "Raspberry Pi 5 – 16GB RAM"

finnjohnsen2 — Thu, 11 Jun 2026 11:49:09 +0000

Remember the good old days of impulse buying the latest Raspberry Pi?

New comment by finnjohnsen2 in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

finnjohnsen2 — Wed, 22 Apr 2026 21:07:02 +0000

Since Gemma 4 came this easter the gap from self hosting models to Claude has decreased sigificantly I think. The gap is still huge it just that local models were extremely non-competitive before easter. So now it seems Qwen 3.6 is another bump up from Gemma 4 which is exciting if it is so. I keep an Opus close ofcourse, because these local models still wander off in the wrong direction and fails. Something Opus almost never does for me anymore.

But every time a local model gets me by - I feel closer to where I should be; writing code should still be free. Both free as in free beer, and free as in freedom.

My setup is a seperate dedicated Ubuntu machine with RTX 5090. Qwen 3.6:27b uses 29/32gb of vram when its working right this minute. I use Ollama in a non root podman instance. And I use OpenCode as ACP Service for my editor, which I highly recommend. ACP (Agent Client Protocol) is how the world should be in case you were asking, which you didnt :)

Exciting times and thank you Qwen team for making the world a better place in a world of Sam Altmans.

New comment by finnjohnsen2 in "DaVinci Resolve – Photo"

finnjohnsen2 — Tue, 14 Apr 2026 19:41:18 +0000

The simulation says you're welcome. Haha, just kidding. This is not a simulation obviously.

New comment by finnjohnsen2 in "Why the US Navy won't blast the Iranians and 'open' Strait of Hormuz"

finnjohnsen2 — Wed, 01 Apr 2026 05:58:20 +0000

TIL: Germany (85m) has almost the same population as Iran (90m)

New comment by finnjohnsen2 in "Moving from GitHub to Codeberg, for lazy people"

finnjohnsen2 — Thu, 26 Mar 2026 17:23:32 +0000

Geopolitics is a reason. Many individuals and companies are scrambling for safe alternatives to US tech. I live in Norway and there is a lot of this going on.