<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: wonderwhyer</title><link>https://news.ycombinator.com/user?id=wonderwhyer</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 18 Apr 2026 11:18:07 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=wonderwhyer" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by wonderwhyer in "A practical guide for setting up Zettelkasten method in Obsidian"]]></title><description><![CDATA[
<p>Actually AI also benefits from thins being organized.
I find Skills to be Zettlekasten inspired or wiki inspired in that sense.<p>Zettlekast has other benefits for humans though. 
If your goal is to grasp lot of knowladge oyu need to do it in atomic way, connect mentally to what you already know and do spaced repetition to internalize.
Zettlkeaste forces you do it it all as part of organizing. Basically by organizing you make it your own.<p>Yes AI can help today but it also means it does not stay in your head.
Not sure its important if it is in your head or you can call AI at any moment instead of your own memory.</p>
]]></description><pubDate>Sat, 11 Apr 2026 14:37:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=47731031</link><dc:creator>wonderwhyer</dc:creator><comments>https://news.ycombinator.com/item?id=47731031</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47731031</guid></item><item><title><![CDATA[New comment by wonderwhyer in "[dead]"]]></title><description><![CDATA[
<p>Anthropic has 98.89% uptime — well below the SaaS gold standard of four nines. 
Yet they tripled enterprise market share in two years.<p>That made me wonder: what is human uptime if measured the same way — against 
a 24/7 clock?<p>Agents are more like humans, not SaaS, not only in how to work with them, in other ways too.
Does it make sense?</p>
]]></description><pubDate>Sat, 04 Apr 2026 20:08:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=47642861</link><dc:creator>wonderwhyer</dc:creator><comments>https://news.ycombinator.com/item?id=47642861</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47642861</guid></item><item><title><![CDATA[Why software was never built for you – and how AI changes that]]></title><description><![CDATA[
<p>Article URL: <a href="https://wonderwhy-er.medium.com/software-was-always-a-compromise-ai-just-broke-it-13b22df1cabf">https://wonderwhy-er.medium.com/software-was-always-a-compromise-ai-just-broke-it-13b22df1cabf</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47435366">https://news.ycombinator.com/item?id=47435366</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 19 Mar 2026 05:38:01 +0000</pubDate><link>https://wonderwhy-er.medium.com/software-was-always-a-compromise-ai-just-broke-it-13b22df1cabf</link><dc:creator>wonderwhyer</dc:creator><comments>https://news.ycombinator.com/item?id=47435366</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47435366</guid></item><item><title><![CDATA[The Bitter Lesson is coming for AI products, not just AI research]]></title><description><![CDATA[
<p>Article URL: <a href="https://wonderwhy-er.medium.com/niche-focus-saved-saas-startups-im-betting-my-ai-startup-on-the-opposite-690699e87fa2">https://wonderwhy-er.medium.com/niche-focus-saved-saas-startups-im-betting-my-ai-startup-on-the-opposite-690699e87fa2</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47200840">https://news.ycombinator.com/item?id=47200840</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 28 Feb 2026 22:11:44 +0000</pubDate><link>https://wonderwhy-er.medium.com/niche-focus-saved-saas-startups-im-betting-my-ai-startup-on-the-opposite-690699e87fa2</link><dc:creator>wonderwhyer</dc:creator><comments>https://news.ycombinator.com/item?id=47200840</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47200840</guid></item><item><title><![CDATA[New comment by wonderwhyer in "MCPs just got a front end, and it's a bigger deal than it sounds"]]></title><description><![CDATA[
<p>For the last year MCPs were backends without a frontend — dumping text into LLM context and hoping it would show it well to the user. Now MCP Apps are here and they could mean way more for MCPs than it seems at first.
Since ChatGPT we've been putting chatbots into our apps. Now we can put our apps into the chatbots. And if one image is worth a thousand words, good UI/UX can be worth ten thousand — without polluting the LLM context window.
I wrote this as someone building an MCP server (Desktop Commander, ~392K installs by now) who felt the pain of having zero UI control firsthand. Happy to answer questions about what building with MCP Apps is actually like.</p>
]]></description><pubDate>Tue, 24 Feb 2026 21:23:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=47143274</link><dc:creator>wonderwhyer</dc:creator><comments>https://news.ycombinator.com/item?id=47143274</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47143274</guid></item><item><title><![CDATA[MCPs just got a front end, and it's a bigger deal than it sounds]]></title><description><![CDATA[
<p>Article URL: <a href="https://wonderwhy-er.medium.com/mcp-apps-ai-just-got-a-frontend-and-we-built-one-cd1f6fc762f6">https://wonderwhy-er.medium.com/mcp-apps-ai-just-got-a-frontend-and-we-built-one-cd1f6fc762f6</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47143273">https://news.ycombinator.com/item?id=47143273</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 24 Feb 2026 21:23:27 +0000</pubDate><link>https://wonderwhy-er.medium.com/mcp-apps-ai-just-got-a-frontend-and-we-built-one-cd1f6fc762f6</link><dc:creator>wonderwhyer</dc:creator><comments>https://news.ycombinator.com/item?id=47143273</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47143273</guid></item><item><title><![CDATA[New comment by wonderwhyer in "How can we compare local LLMs vs. APIs vs. subscriptions objectively?"]]></title><description><![CDATA[
<p>The debate around local vs API vs subscriptions feels mostly anecdotal.
I tried building a tool that compares them using “quality-adjusted tokens per dollar.”<p>The idea:<p>Tokens per dollar<p>Weighted input/output pricing (75/25 assumption)<p>Benchmark-normalized quality (Arena, Aider, SWE-bench)<p>Early results surprised me (local often loses economically unless privacy is heavily valued).<p>I’m mostly looking for critique of the methodology:<p>Is quality-adjusted tokens per dollar even the right metric?<p>Is normalizing ELO to % defensible?<p>What benchmarks am I missing?</p>
]]></description><pubDate>Tue, 24 Feb 2026 08:07:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=47134268</link><dc:creator>wonderwhyer</dc:creator><comments>https://news.ycombinator.com/item?id=47134268</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47134268</guid></item><item><title><![CDATA[How can we compare local LLMs vs. APIs vs. subscriptions objectively?]]></title><description><![CDATA[
<p>Article URL: <a href="https://wonderwhy-er.medium.com/local-llms-are-finally-beating-the-cloud-but-are-they-51fc0ad0dbd7">https://wonderwhy-er.medium.com/local-llms-are-finally-beating-the-cloud-but-are-they-51fc0ad0dbd7</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47134267">https://news.ycombinator.com/item?id=47134267</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 24 Feb 2026 08:07:40 +0000</pubDate><link>https://wonderwhy-er.medium.com/local-llms-are-finally-beating-the-cloud-but-are-they-51fc0ad0dbd7</link><dc:creator>wonderwhyer</dc:creator><comments>https://news.ycombinator.com/item?id=47134267</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47134267</guid></item><item><title><![CDATA[New comment by wonderwhyer in "Show HN: Desktop Commander MCP+Claude = Local Automation with fixed flat price"]]></title><description><![CDATA[
<p>Great staff, do you know how to add github pages?
And may be add a link to desktop commander too.</p>
]]></description><pubDate>Wed, 09 Apr 2025 07:25:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=43629685</link><dc:creator>wonderwhyer</dc:creator><comments>https://news.ycombinator.com/item?id=43629685</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43629685</guid></item><item><title><![CDATA[New comment by wonderwhyer in "Show HN: Browser MCP – Automate your browser using Cursor, Claude, VS Code"]]></title><description><![CDATA[
<p>I would probably call it shipping containers for LLM tool integrations.<p>Containers are not a big deal when viewed in isolation. But when its common size/standard for all kinds of ships, cranes and trucks, it is a big deal then.<p>In that sense its more about gathering community around one way to do things.<p>In theory there are REST APIs and OpenAPI standard, but those were not made for LLMs but code.
So you usually need some kind of friendly wrapper(like for candy) on top of REST API.<p>It really starts to feel like a a big deal when you work in integrating LLMs with tools.</p>
]]></description><pubDate>Tue, 08 Apr 2025 10:37:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=43620153</link><dc:creator>wonderwhyer</dc:creator><comments>https://news.ycombinator.com/item?id=43620153</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43620153</guid></item></channel></rss>