<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: y42</title><link>https://news.ycombinator.com/user?id=y42</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sun, 26 Apr 2026 21:27:31 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=y42" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by y42 in "Show HN: I remade my blog into a Windows 3.1 environment"]]></title><description><![CDATA[
<p>reminds me of that:<p><a href="https://institut-fdh.de/" rel="nofollow">https://institut-fdh.de/</a><p>but your's is way better implemented it seems - very nice!<p>(disclaimer: it's my site, <i>shameless-plug</i>)</p>
]]></description><pubDate>Sun, 26 Apr 2026 16:44:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=47911659</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=47911659</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47911659</guid></item><item><title><![CDATA[New comment by y42 in "Show HN: Sig – personal & team knowledge base built from your work conversations"]]></title><description><![CDATA[
<p>I like the clean style, I was working on something similar, but never reached that readines-level.<p>However, the first screen seems a little contra productive. User entered a paragraph and in return gets a "summary" - but it feels so long. It's probably okay... it just triggered me very first impulse.<p>And what remains unclear is the meaning of "Team Sync". What's happening there? Is it a "group chat" or does it sends messages?<p>Speaking of... what about integrations with like Teams, Slack, Discord? I know that Teams offers a Meeting Summary which would be great if you could directly store it in _sig_.</p>
]]></description><pubDate>Sat, 25 Apr 2026 17:17:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=47902970</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=47902970</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47902970</guid></item><item><title><![CDATA[New comment by y42 in "I cancelled Claude: Token issues, declining quality, and poor support"]]></title><description><![CDATA[
<p>I like your blog and I can totally relate to this article - it's like something I wanted to write about for a couple of weeks now. :D<p><a href="https://thoughts.jock.pl/p/adhd-ai-agent-personal-experience-2026" rel="nofollow">https://thoughts.jock.pl/p/adhd-ai-agent-personal-experience...</a></p>
]]></description><pubDate>Fri, 24 Apr 2026 21:33:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=47896081</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=47896081</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47896081</guid></item><item><title><![CDATA[New comment by y42 in "I cancelled Claude: Token issues, declining quality, and poor support"]]></title><description><![CDATA[
<p><a href="https://news.ycombinator.com/item?id=47894155">https://news.ycombinator.com/item?id=47894155</a><p>(I am just learning that "a couple of weeks" apparently means "2 weeks"...)</p>
]]></description><pubDate>Fri, 24 Apr 2026 20:59:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=47895733</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=47895733</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47895733</guid></item><item><title><![CDATA[New comment by y42 in "I Cancelled Claude: Token Issues, Declining Quality, and Poor Support"]]></title><description><![CDATA[
<p>I am trying Qwen3.5-9B-Claude-4.6 since a couple of days now locally coming from OMLX. Either via Hermes or Continue in VS Code. It's oka'ish, even performance-wise.<p>[1] <a href="https://huggingface.co/Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF" rel="nofollow">https://huggingface.co/Jackrong/Qwen3.5-9B-Claude-4.6-Opus-R...</a></p>
]]></description><pubDate>Fri, 24 Apr 2026 18:15:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=47893916</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=47893916</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47893916</guid></item><item><title><![CDATA[New comment by y42 in "I Cancelled Claude: Token Issues, Declining Quality, and Poor Support"]]></title><description><![CDATA[
<p>I dare to call meself a senior dev, so I don't need a replacement, I need a tool.</p>
]]></description><pubDate>Fri, 24 Apr 2026 16:59:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=47892900</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=47892900</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47892900</guid></item><item><title><![CDATA[New comment by y42 in "I cancelled Claude: Token issues, declining quality, and poor support"]]></title><description><![CDATA[
<p>That's what I am thinking, too. It sound's like a conspiracy theory, but at the end Anthropic et al benefits from models that don't finish their jobs. I recently read about this "over editing phenomenon". The machine is never done. It doesn't want to.<p>It's like dating apps. They don't want you to find a good match, because then you cancel the subscription.</p>
]]></description><pubDate>Fri, 24 Apr 2026 16:55:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=47892835</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=47892835</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47892835</guid></item><item><title><![CDATA[I cancelled Claude: Token issues, declining quality, and poor support]]></title><description><![CDATA[
<p>Article URL: <a href="https://nickyreinert.de/en/2026/2026-04-24-claude-critics/">https://nickyreinert.de/en/2026/2026-04-24-claude-critics/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47892019">https://news.ycombinator.com/item?id=47892019</a></p>
<p>Points: 957</p>
<p># Comments: 574</p>
]]></description><pubDate>Fri, 24 Apr 2026 15:59:19 +0000</pubDate><link>https://nickyreinert.de/en/2026/2026-04-24-claude-critics/</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=47892019</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47892019</guid></item><item><title><![CDATA[New comment by y42 in "How to run Qwen 3.5 locally"]]></title><description><![CDATA[
<p>> consumer-grade hardware<p>Not disagreeing per se, but a quick look at the installation instructions confirms what I assumed:<p>Yeah, you can run a highly quantized version on your 2020 Nvidia GPU. But:<p>- When inferencing, it occupies your "whole machine.". At least you have a modern interactive heating feature in your flat.<p>- You need to follow eleven-thousand nerdy steps to get it running; my mum is really looking forward to that.<p>- Not to mention the pain you went through installing Nvidia drivers; nothing my mum will ever manage in the near future.<p>... and all this to get something that merely competes with Haiku.<p>Don't get me wrong - I am exaggerating, I know.  It's important to have competition and the opportunity to run "AI" on your own metal. But this reminds me of the early days of smartphones and my old XDA Neo. Sure, it was damn smart, and I remember all those jealous faces because of my "device from the future." But oh boy, it was also a PITA maintaining it.<p>Here we are now. Running AI locally is a sneak peek into the future. But as long as you need a CS degree and hardware worth a small car to achieve reasonable results, it's far from mainstream. Therefore, "consumer-grade hardware" sounds like a euphemism here.<p>I like how we nerds are living in our buble celebrating this stuff while 99% of mankind still doomscroll through facebook and laughing at (now AI generated) brain rot.<p>(No offense (ʘ‿ʘ)╯)</p>
]]></description><pubDate>Sun, 08 Mar 2026 19:41:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=47300504</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=47300504</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47300504</guid></item><item><title><![CDATA[New comment by y42 in "How will OpenAI compete?"]]></title><description><![CDATA[
<p>Why would you want to move conversations with you? I use multiple different models, I don't care about the history.<p>My "brain" in terms of projects, is local on my computer. I have a simple set of system rules that I need to copy.<p>I am not everyone, I understand that. What I try to say: don't overestimate the lock in effect of AI. I doubt there is one.</p>
]]></description><pubDate>Thu, 26 Feb 2026 11:39:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=47164696</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=47164696</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47164696</guid></item><item><title><![CDATA[New comment by y42 in "Show HN: Cc-md – Zero-cost Obsidian sync across iPhone, Mac, and GitHub"]]></title><description><![CDATA[
<p>Can you explain how you achieved it? I don't find it in your repo, I am too tired probably? However, I tried something different but stuck eventually with the receiving part on Android. One cannot just pull files from somewhere and put them into the Obsidian folder. I mean, not without efforts.</p>
]]></description><pubDate>Sat, 21 Feb 2026 21:58:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=47105255</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=47105255</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47105255</guid></item><item><title><![CDATA[Show HN: MeMCP – MCP for Personal Profile]]></title><description><![CDATA[
<p>This is a small side project that kind of escalated: meMCP. It’s a "personal profile protocol," which means it holds data about your professional milestones, education, side projects, and whatever else you feed it. It consists of two parts:<p>> Backend with scrapers, crawlers, and processors to read data from different sources—primarily LinkedIn for professional history, but also RSS feeds or even Medium (provided you export the raw DOM from your stories overview). Right now, the "connectors" are somewhat limited, as I’ve focused on platforms I actually use. Everything you input is classified into skills, technologies, and general tags. A few metrics are then calculated to score proficiency or the relevance of your capabilities.<p>> Frontend for your favorite LLM/Agent. It contains everything needed to allow any agent to interact with this MCP. A use case would be generating a CV for job applications, drafting cover letters, or simply showcasing your achievements.<p>See it in action:<p><a href="https://mcp.nickyreinert.de/?lang=en" rel="nofollow">https://mcp.nickyreinert.de/?lang=en</a><p>or<p><a href="https://mcp.nickyreinert.de/human" rel="nofollow">https://mcp.nickyreinert.de/human</a><p>I know someone built something similar years ago, but I couldn't find it and I am not sure, if this was MCP, too?<p>Tell me what you think.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47104987">https://news.ycombinator.com/item?id=47104987</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 21 Feb 2026 21:29:15 +0000</pubDate><link>https://github.com/nickyreinert/meMCP</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=47104987</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47104987</guid></item><item><title><![CDATA[New comment by y42 in "AI adoption and Solow's productivity paradox"]]></title><description><![CDATA[
<p>Problem is, that just having a Claude subscription doesn't make you productive. Most of those talks happen in a "tech'ish" environments. Not every business is about coding.<p>Real life example: A client came to me asking how to compare orders against order confirmation from the vendor. They come as PDF files. Which made me wonder: Wait, you don't have any kind of API or at least structured data that the vendor gives you?<p>Nope.<p>And here you are. I am not talking about a niche business. I assume that's a broader problem. Tech can probably automate everything and this since 30 years. Still business lack of "proper" IT processes, because at the end every company is unique and requires particular measures to be "fully" onboarded to IT based improvements like that.</p>
]]></description><pubDate>Wed, 18 Feb 2026 08:50:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=47058798</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=47058798</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47058798</guid></item><item><title><![CDATA[New comment by y42 in "Four Column ASCII (2017)"]]></title><description><![CDATA[
<p>first I was like "What but why? You don't save any space or what's that excercise about" then I read it again and it blew my mind. I thought I knew everything about ASCII. What a fool I am, Sokrates was right. Always.</p>
]]></description><pubDate>Tue, 17 Feb 2026 13:49:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=47047453</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=47047453</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47047453</guid></item><item><title><![CDATA[New comment by y42 in "Four Column ASCII (2017)"]]></title><description><![CDATA[
<p>only that would have broken the whole thing back in the days ;)</p>
]]></description><pubDate>Tue, 17 Feb 2026 13:45:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=47047421</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=47047421</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47047421</guid></item><item><title><![CDATA[New comment by y42 in "I made 20 GDPR deletion requests. 12 were ignored"]]></title><description><![CDATA[
<p>That’s essentially what I’ve experienced, call it 'anecdotal evidence.'<p>I had a long, ongoing, and very upsetting interaction with a  bigger German company. Since I have experience in data privacy and GDPR, I eventually started thoroughly crawling their entire online presence for infringements.
 I found a significant number of issues and compiled a very extensive report. At first, they were completely dismissive. It was only after I issued formal legal warnings that an actual lawyer contacted me and promised to fix the issues.<p>Most of the GDPR violations were simply sloppy, though some were genuinely ignorant. It’s wild that we are eight years past 'Year Zero,' and while everyone is constantly talking about data privacy, these gaps still exist.<p>Some of them eventually has been fixed after my report, silently of course. phhh...</p>
]]></description><pubDate>Tue, 03 Feb 2026 18:46:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=46875331</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=46875331</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46875331</guid></item><item><title><![CDATA[New comment by y42 in "I made 20 GDPR deletion requests. 12 were ignored"]]></title><description><![CDATA[
<p>can you explain why? I mean a company ignoring common and simple rules of law... why you want to "protect" that?</p>
]]></description><pubDate>Tue, 03 Feb 2026 18:37:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=46875184</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=46875184</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46875184</guid></item><item><title><![CDATA[New comment by y42 in "Maze Algorithms (2017)"]]></title><description><![CDATA[
<p>Sure will do, thanks! (first time I am hearing about the "SCP")</p>
]]></description><pubDate>Sun, 25 Jan 2026 19:20:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=46757238</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=46757238</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46757238</guid></item><item><title><![CDATA[New comment by y42 in "Maze Algorithms (2017)"]]></title><description><![CDATA[
<p>of course!  :D
(how to approach the development of a maze algorithm)<p><a href="https://news.ycombinator.com/item?id=23131983">https://news.ycombinator.com/item?id=23131983</a></p>
]]></description><pubDate>Sat, 24 Jan 2026 19:14:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=46746580</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=46746580</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46746580</guid></item><item><title><![CDATA[New comment by y42 in "80386 Multiplication and Division"]]></title><description><![CDATA[
<p>or probably just some kind of preference/selection bias.<p>You own a  red Mercedes now and suddenly you see only red Mercedes' on the streets.</p>
]]></description><pubDate>Sat, 24 Jan 2026 11:25:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=46742692</link><dc:creator>y42</dc:creator><comments>https://news.ycombinator.com/item?id=46742692</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46742692</guid></item></channel></rss>