<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: finnjohnsen2</title><link>https://news.ycombinator.com/user?id=finnjohnsen2</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 23 Sep 2026 09:15:24 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=finnjohnsen2" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by finnjohnsen2 in "Grok 4.7"]]></title><description><![CDATA[
<p>Is Grok relevant? Who uses it?<p>Maybe I'm in some kind of bouble but I have never met or talked to anyone who has used Grok.</p>
]]></description><pubDate>Mon, 21 Sep 2026 20:25:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=49792903</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=49792903</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49792903</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "Qwen Image 2.1"]]></title><description><![CDATA[
<p>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.</p>
]]></description><pubDate>Mon, 21 Sep 2026 11:42:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=49785986</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=49785986</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49785986</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "Qwen Image 2.1"]]></title><description><![CDATA[
<p>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.<p>I have FLUX.2 klein and dev, Ideogram, LaDA-Image and SenseNova locally. Works great. Ive never touched a file.<p>The days of making container yamls myself is over. I read them but I dont edit anymore.</p>
]]></description><pubDate>Sun, 20 Sep 2026 18:34:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=49778587</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=49778587</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49778587</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "Qwen-Image-2.1: Compact, efficient, and unified image creation"]]></title><description><![CDATA[
<p>I would call this a license trap: Qwen RESEARCH LICENSE AGREEMENT<p>Code on github, models on huggingface, nice intro text: "We are excited to open-source Qwen-Image-2.1 [...]".<p>meh...</p>
]]></description><pubDate>Sun, 20 Sep 2026 18:18:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=49778420</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=49778420</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49778420</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "Muse Spark 1.3"]]></title><description><![CDATA[
<p>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.<p>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.</p>
]]></description><pubDate>Wed, 02 Sep 2026 19:52:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=49541502</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=49541502</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49541502</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "Claude Fable 5.1 and Claude Mythos 5.1"]]></title><description><![CDATA[
<p>OpenCode+GLM-5.3 (and 5.2) for three weeks solid. Im so happy I made it out</p>
]]></description><pubDate>Tue, 01 Sep 2026 21:19:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=49528360</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=49528360</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49528360</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "Mark Zuckerberg attacks 'closed' AI rivals as Meta returns to open models"]]></title><description><![CDATA[
<p>We don't trust you Zuck but we'll take it. Thanks.</p>
]]></description><pubDate>Tue, 11 Aug 2026 13:25:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=49257932</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=49257932</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49257932</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "ZCode – Harness for GLM-5.2"]]></title><description><![CDATA[
<p>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</p>
]]></description><pubDate>Thu, 02 Jul 2026 13:30:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=48761303</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=48761303</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48761303</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "U.S. government will decide who gets to use GPT-5.6"]]></title><description><![CDATA[
<p>Less money to US AI tech. This could be good long term to move us away from them.</p>
]]></description><pubDate>Fri, 26 Jun 2026 21:11:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=48692014</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=48692014</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48692014</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "Raspberry Pi 5 – 16GB RAM"]]></title><description><![CDATA[
<p>Remember the good old days of impulse buying the latest Raspberry Pi?</p>
]]></description><pubDate>Thu, 11 Jun 2026 11:49:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=48489081</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=48489081</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48489081</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"]]></title><description><![CDATA[
<p>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.<p>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.<p>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 :)<p>Exciting times and thank you Qwen team for making the world a better place in a world of Sam Altmans.</p>
]]></description><pubDate>Wed, 22 Apr 2026 21:07:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=47869285</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=47869285</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47869285</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "DaVinci Resolve – Photo"]]></title><description><![CDATA[
<p>The simulation says you're welcome. Haha, just kidding. This is not a simulation obviously.</p>
]]></description><pubDate>Tue, 14 Apr 2026 19:41:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=47770453</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=47770453</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47770453</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "Why the US Navy won't blast the Iranians and 'open' Strait of Hormuz"]]></title><description><![CDATA[
<p>TIL: Germany (85m) has almost the same population as Iran (90m)</p>
]]></description><pubDate>Wed, 01 Apr 2026 05:58:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=47597337</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=47597337</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47597337</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "Moving from GitHub to Codeberg, for lazy people"]]></title><description><![CDATA[
<p>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.</p>
]]></description><pubDate>Thu, 26 Mar 2026 17:23:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=47533188</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=47533188</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47533188</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "Hetzner Prices increase 30-40%"]]></title><description><![CDATA[
<p>Sir, your logic is flawed. You can buy Adidas in the US too.  Adidas is still 0% american.</p>
]]></description><pubDate>Tue, 24 Feb 2026 14:18:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=47137457</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=47137457</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47137457</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "AI is not a coworker, it's an exoskeleton"]]></title><description><![CDATA[
<p>I would disagree. Amplified meens me and you get more s** done.<p>Unless there a limited amount of software we need to produce per year globally to keep everyone happy, then nobody wants more -- and we happen to be at that point right NOW this second.<p>I think not. We can make more (in less time) and people will get more. This is the mental "glass half full" approach I think. Why not take this mental route instead? We don't know the future anyway.</p>
]]></description><pubDate>Thu, 19 Feb 2026 22:05:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=47080225</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=47080225</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47080225</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "AI is not a coworker, it's an exoskeleton"]]></title><description><![CDATA[
<p>I like this. This is an accurate state of AI at this very moment for me. The LLM is (just) a tool which is making me "amplified" for coding and certain tasks.<p>I will worry about developers being completely replaced when I see something resembling it. Enough people worry about that (or say it to amp stock prices) -- and they like to tell everyone about this future too. I just don't see it.</p>
]]></description><pubDate>Thu, 19 Feb 2026 21:58:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=47080116</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=47080116</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47080116</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "Qwen-Image-2.0: Professional infographics, exquisite photorealism"]]></title><description><![CDATA[
<p>I agree. They makes me nauseous. The same kind of light nausea as car sickness.<p>I assume our brains are used to stuff which we dont notice conciously, and reject very mild errors. I've stared at the picture a bit now and the finger holding the baloon is weird. The out of place snowman feels weird. If you follow the background blur around it isnt at the same depth everywehere. Everything that reflects, has reflections that I cant see in the scene.<p>I dont feel good staring at it now so I had to stop.</p>
]]></description><pubDate>Tue, 10 Feb 2026 10:25:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=46957740</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=46957740</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46957740</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "EU and Mercosur countries sign landmark free trade deal"]]></title><description><![CDATA[
<p>Me too. I just think he needs to pick his battles right now as Greenland is taking so much space.</p>
]]></description><pubDate>Sun, 18 Jan 2026 11:14:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=46666828</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=46666828</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46666828</guid></item><item><title><![CDATA[New comment by finnjohnsen2 in "Ask HN: What Are You Working On? (December 2025)"]]></title><description><![CDATA[
<p>I am learning Unreal Engine for a year. im almost half way through and am making a simple Space Invaders clone which I will publish on steam for free.</p>
]]></description><pubDate>Mon, 15 Dec 2025 17:43:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=46277733</link><dc:creator>finnjohnsen2</dc:creator><comments>https://news.ycombinator.com/item?id=46277733</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46277733</guid></item></channel></rss>