<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: recued</title><link>https://news.ycombinator.com/user?id=recued</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 29 Oct 2026 23:18:25 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=recued" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by recued in "Ask HN: What are your most ambitious projects in 2026?"]]></title><description><![CDATA[
<p>I started planning for this project in February, began coding in April, first release in July, and been active daily till today.<p>At first I was only trying to make a tool that makes my day easier, I want AI to follow the exact procedure to perform my requests, soon I realize almost 80% of the "expected procedure" is deterministic without even needing AI, in most cases AI is only needed in judge/review/summarize/orchestrate actions, all the rest of the dirty work can be done without AI and without paying a dime.<p>As a result I created <a href="https://github.com/recued/recued" rel="nofollow">https://github.com/recued/recued</a>, it stores all my data in my own home, executes predefined recipes whenever I ask for, fast, and cheaply.<p>Is it a success? I don't know, but I am still actively improving it on daily basis.<p>I guess neither success nor failure fits my description, I found something that I am passionated about, and it is also making my day easier.<p>From the sentimental perspective, I call it my success.</p>
]]></description><pubDate>Sun, 25 Oct 2026 07:20:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=50229110</link><dc:creator>recued</dc:creator><comments>https://news.ycombinator.com/item?id=50229110</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50229110</guid></item><item><title><![CDATA[New comment by recued in "Is AI just another get rich quick scheme?"]]></title><description><![CDATA[
<p>I think AI is more like the fundamental layer kind of changing, that reshape the values, rules and perspectives in modern society. Examples: inventions of paper, gunpowder, train, airplane, internet, and now AI. No body can claim the ownership of this change, and everybody can participate in some ways, selling it, using it etc.</p>
]]></description><pubDate>Sun, 25 Oct 2026 06:04:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=50228770</link><dc:creator>recued</dc:creator><comments>https://news.ycombinator.com/item?id=50228770</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50228770</guid></item><item><title><![CDATA[New comment by recued in "Ask HN: If the models are so good, why doesn't OpenAI just start 100 companies?"]]></title><description><![CDATA[
<p>eventually there will be no other 100 companies, when AI has enough storage to store all your data, query, reason and answer much faster, there will be no need for other softwares, and saas.</p>
]]></description><pubDate>Sat, 24 Oct 2026 00:28:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=50217183</link><dc:creator>recued</dc:creator><comments>https://news.ycombinator.com/item?id=50217183</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50217183</guid></item><item><title><![CDATA[New comment by recued in "The Role of Humans in Software Factories"]]></title><description><![CDATA[
<p>I worked 16 hours a day for the past 6 months on 1 single project, with 6-9 concurrent sessions as regular/daily routines, I can say that the bottleneck is human judgment. AI can help to speed up the progress, shrinking weeks of dev works into hours, but it is human's job to take the wheel and pave the way to achieving the objectives. I think we are at a golden age: theories can be validated faster, ideas can be realized sooner, and cheaper.</p>
]]></description><pubDate>Fri, 23 Oct 2026 15:34:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=50210763</link><dc:creator>recued</dc:creator><comments>https://news.ycombinator.com/item?id=50210763</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50210763</guid></item><item><title><![CDATA[New comment by recued in "AI Agents Kinda Broke the Internet"]]></title><description><![CDATA[
<p>yes but for the better right? It found loopholes for us to decide to fix. I think there's a more important angle to consider: is it AI agent's doing, or is the news travel much faster than before. If these bugs were found by hand, it may not make that much of a noise spreading across the world in 24 hours, AI agent topic gets more attentions and travel faster, which also makes the threat more serious due to the wide spread. In all fairness, this is actually for the better in my point of view.</p>
]]></description><pubDate>Fri, 23 Oct 2026 15:23:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=50210598</link><dc:creator>recued</dc:creator><comments>https://news.ycombinator.com/item?id=50210598</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50210598</guid></item><item><title><![CDATA[New comment by recued in "AI compute is the new oil–and needs a new market"]]></title><description><![CDATA[
<p>the concern is real because the current market is treating AI as "hand off and controlling all" agent, which is not efficient and not desirable because AI is still not smart enough to take on this initiative yet, and most of the work (especially repeatable ones don't need full AI. I would guess 5-10% of our current spending is actually usefully achieving some positive outcomes, the rest are just wasted. But the global resources pouring into AI field is the real trend.</p>
]]></description><pubDate>Fri, 23 Oct 2026 04:33:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=50204548</link><dc:creator>recued</dc:creator><comments>https://news.ycombinator.com/item?id=50204548</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50204548</guid></item></channel></rss>