<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: ch3coohlink</title><link>https://news.ycombinator.com/user?id=ch3coohlink</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 05 Jun 2026 04:14:19 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=ch3coohlink" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by ch3coohlink in "I'm Done Using AI"]]></title><description><![CDATA[
<p>Also, I was wondering why posts that don't start with 'Ask HN' still show up in the Ask section? Just asking out of curiosity, since I'm a newbie here.</p>
]]></description><pubDate>Fri, 05 Jun 2026 02:07:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=48407134</link><dc:creator>ch3coohlink</dc:creator><comments>https://news.ycombinator.com/item?id=48407134</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48407134</guid></item><item><title><![CDATA[New comment by ch3coohlink in "I'm Done Using AI"]]></title><description><![CDATA[
<p>I think it really depends on the person and your existing workflow. For me personally, I find LLMs to be a great pair-programming partner that helps me stay focused even on mundane tasks. When it comes to truly difficult problems, their input can definitely get annoying sometimes, but at the very least, they can be delegated to do massive amounts of verification work. It's an easy way to get a wealth of empirical data to back up my decisions.</p>
]]></description><pubDate>Fri, 05 Jun 2026 02:01:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=48407099</link><dc:creator>ch3coohlink</dc:creator><comments>https://news.ycombinator.com/item?id=48407099</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48407099</guid></item><item><title><![CDATA[New comment by ch3coohlink in "They’re made out of weights"]]></title><description><![CDATA[
<p>I think it's simply because we haven't found a better algorithm than backpropagation. We're stuck relying on massive datasets, running the numbers over and over, and working backward from errors to figure out how to fine-tune trillions of 'knobs.' Then, we have to do this at least once for every single token across the entire internet. Any tiny bit of computation, when multiplied by a base that massive, inevitably skyrockets into astronomical numbers.</p>
]]></description><pubDate>Thu, 04 Jun 2026 09:29:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=48396206</link><dc:creator>ch3coohlink</dc:creator><comments>https://news.ycombinator.com/item?id=48396206</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48396206</guid></item><item><title><![CDATA[Proposing a solution for recording intent by reimagining version control [video]]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.youtube.com/watch?v=IFbj-P0D1AQ">https://www.youtube.com/watch?v=IFbj-P0D1AQ</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46128830">https://news.ycombinator.com/item?id=46128830</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 03 Dec 2025 00:30:37 +0000</pubDate><link>https://www.youtube.com/watch?v=IFbj-P0D1AQ</link><dc:creator>ch3coohlink</dc:creator><comments>https://news.ycombinator.com/item?id=46128830</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46128830</guid></item><item><title><![CDATA[New comment by ch3coohlink in "Ask HN: Simplest way to productize my graph layout algo?"]]></title><description><![CDATA[
<p>Ideally, a business.</p>
]]></description><pubDate>Fri, 28 Mar 2025 12:47:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=43504723</link><dc:creator>ch3coohlink</dc:creator><comments>https://news.ycombinator.com/item?id=43504723</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43504723</guid></item><item><title><![CDATA[New comment by ch3coohlink in "Ask HN: Simplest way to productize my graph layout algo?"]]></title><description><![CDATA[
<p>I don't even realize mermaid has a paid plan, thx for pointing that.</p>
]]></description><pubDate>Fri, 28 Mar 2025 12:43:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=43504676</link><dc:creator>ch3coohlink</dc:creator><comments>https://news.ycombinator.com/item?id=43504676</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43504676</guid></item><item><title><![CDATA[Ask HN: Simplest way to productize my graph layout algo?]]></title><description><![CDATA[
<p>I've developed an algorithm that produces good planar layouts for graphs with arbitrary structures. (Obviously, extremely non-planar graphs won't yield great results, but it works well on the kinds of graphs you'd encounter in practice.) It's similar to Graphviz's dot, but I believe my algorithm produces better layouts, and the entire process is real-time and iterative, allowing users to add or remove nodes/edges mid-process without the long wait times of Graphviz.<p>I can provide some layout examples from earlier versions if anyone is interested.<p>Now I'm trying to productize this algorithm, but the options are overwhelming. Graph visualization has so many potential applications, such as real-time visualization of programming language semantics (control flow graphs, dependency graphs, event triggering graphs), a visual heap memory debugger, or an improved node editor. I know these applications are genuinely useful, but I'm concerned about the long development cycles. I'm leaning towards simpler tools, like a mind map editor. Traditional mind map tools only support tree-like structures (with some manually-controlled extra edges), but my algorithm can automatically lay out arbitrary graph structures, which I think could be quite appealing.<p>First time posting – I hope my question is clear and relevant!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43504476">https://news.ycombinator.com/item?id=43504476</a></p>
<p>Points: 2</p>
<p># Comments: 6</p>
]]></description><pubDate>Fri, 28 Mar 2025 12:21:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=43504476</link><dc:creator>ch3coohlink</dc:creator><comments>https://news.ycombinator.com/item?id=43504476</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43504476</guid></item></channel></rss>