<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: g_br_l</title><link>https://news.ycombinator.com/user?id=g_br_l</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 01 Sep 2026 08:33:40 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=g_br_l" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by g_br_l in "Do you really need an agent?"]]></title><description><![CDATA[
<p>I honestly don't know. I think one of the reasons openclaw specifically got so popular is because it reached a certain critical mass (in popularity) that made it become sort of the "first contact" with an agent for a certain, less/non technical audience - in the sense that it showed them features that they didn't know could be achieved with other, already existing tools.<p>just speculating though.</p>
]]></description><pubDate>Tue, 17 Mar 2026 12:44:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=47411871</link><dc:creator>g_br_l</dc:creator><comments>https://news.ycombinator.com/item?id=47411871</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47411871</guid></item><item><title><![CDATA[Show HN: The Crawl Times – Newspaper-style front pages for tech news sites]]></title><description><![CDATA[
<p>I built a small experiment that crawls tech-news-adjacent sites (like HN) and generates a newspaper-style front page for each one. This was inspired by Cloudflare's recent (controversial?) release of their /crawl API.<p>It runs periodic crawls, picks up the top stories, and lays them out in a classic broadsheet format: top story, trending section, briefs, etc. Basically a daily edition of your favorite tech site.<p>Nothing serious, just a weeknight project to play with Cloudflare's /crawl API and a few of their other tech offerings (workers, D1, etc.). I'm not in any way sponsored by CF, but if you're from CF and you're reading this I really dig your stack and you should give me credits to fund these dumb projects thank you very much.<p>Home page: <a href="https://crawltimes.com/" rel="nofollow">https://crawltimes.com/</a></p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47411470">https://news.ycombinator.com/item?id=47411470</a></p>
<p>Points: 5</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 17 Mar 2026 12:00:43 +0000</pubDate><link>https://crawltimes.com/hacker-news</link><dc:creator>g_br_l</dc:creator><comments>https://news.ycombinator.com/item?id=47411470</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47411470</guid></item><item><title><![CDATA[New comment by g_br_l in "Do you really need an agent?"]]></title><description><![CDATA[
<p>more agents, I guess</p>
]]></description><pubDate>Sun, 15 Mar 2026 21:34:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=47392198</link><dc:creator>g_br_l</dc:creator><comments>https://news.ycombinator.com/item?id=47392198</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47392198</guid></item><item><title><![CDATA[Do you really need an agent?]]></title><description><![CDATA[
<p>I'm an engineer. I use AI both for my work and my personal life, basically every single day. I don't think "AI is a fad".<p>Here's the thing, though: For the past few months "agent" has been the buzzword. 99% of people talking about it have no clue how it works or what it is exactly, but it's <i>the thing</i>.<p>"Yo, I'm running 39 parallel openclaws in my 45k Mac Mini tower I built at home"
"man these are making me <i>so</i> productive, I'm producing so much stuff you can't even begin to comprehend it"
"this changes everything."<p>You've read at least ~50 variants of each of these. You see it all the time, to the point where you're wondering whether maybe you're missing out on it - maybe you really are "not gonna make it". And while thinking this you scroll down and another related post shows up.<p>This has pissed me off so much my hand has been forced to post here this half rant, half discussion starter: Do you <i>really</i> need a personal agent? Are you really spending so much time every day on the minor tasks it can do, that you actually trust it -unsupervised- to do them for you? Is it really worth the risk letting <current SOTA model> respond to your emails for you? Have you actually thought of how screwed you could be if it just... does the wrong thing?<p>I really can't stop coming up with questions like these every time I see one more of these posts, one more analysis on what the best set up for your personal agent is today (which is just so much better than it was 5 days ago I swear!).<p>I see the timeline and can't help but think: there's no way <i>this many</i> people have <i>so much</i> work that can be automated... right? And if they do have so much work that is easily automated - was that work worth doing anyway?<p>THE ACTUAL QUESTION: Have any of you actually set up a personal agent and kept using it 2 weeks after? Has it actually helped you with your daily tasks in any noticeable way? Am I really not gonna make it by not buying a Mac Mini?<p>That's it, I'm not promoting anything or building the next agentic startup btw.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47390937">https://news.ycombinator.com/item?id=47390937</a></p>
<p>Points: 9</p>
<p># Comments: 6</p>
]]></description><pubDate>Sun, 15 Mar 2026 19:24:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=47390937</link><dc:creator>g_br_l</dc:creator><comments>https://news.ycombinator.com/item?id=47390937</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47390937</guid></item><item><title><![CDATA[New comment by g_br_l in "Can I run AI locally?"]]></title><description><![CDATA[
<p>could you add raspi to the list to see which ridiculously small models it can run?</p>
]]></description><pubDate>Fri, 13 Mar 2026 16:31:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=47366556</link><dc:creator>g_br_l</dc:creator><comments>https://news.ycombinator.com/item?id=47366556</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47366556</guid></item></channel></rss>