<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: dkalola</title><link>https://news.ycombinator.com/user?id=dkalola</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 28 Apr 2026 23:47:11 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=dkalola" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by dkalola in "Show HN: LLM Sorter – Python package to sort lists of items using LLM calls"]]></title><description><![CDATA[
<p>Yes, that's right. This is not a practical approach given current LLM limitations. But perhaps in the future if the cost of each individual call decreases, and if latency decreases (and models run locally), but context window remains limited this approach could be more useful as it uses pairwise comparisons rather than loading the entire context window.</p>
]]></description><pubDate>Mon, 29 Dec 2025 01:20:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=46416327</link><dc:creator>dkalola</dc:creator><comments>https://news.ycombinator.com/item?id=46416327</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46416327</guid></item><item><title><![CDATA[Show HN: LLM Sorter – Python package to sort lists of items using LLM calls]]></title><description><![CDATA[
<p>Just a quick experiment I thought of building. Limited practical usage, for sure.<p>A Python library that uses LLMs as comparators for semantic sorting. Sort any list by meaning, tone, complexity, urgency, or any criteria expressible in natural language. This library uses an OpenRouter API key to interface with LLM providers.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46402797">https://news.ycombinator.com/item?id=46402797</a></p>
<p>Points: 1</p>
<p># Comments: 2</p>
]]></description><pubDate>Sat, 27 Dec 2025 16:14:45 +0000</pubDate><link>https://github.com/kalolad1/llm-sorter</link><dc:creator>dkalola</dc:creator><comments>https://news.ycombinator.com/item?id=46402797</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46402797</guid></item><item><title><![CDATA[New comment by dkalola in "History LLMs: Models trained exclusively on pre-1913 texts"]]></title><description><![CDATA[
<p>How can we interact with such models? Is there a web application interface?</p>
]]></description><pubDate>Sat, 20 Dec 2025 00:54:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=46332761</link><dc:creator>dkalola</dc:creator><comments>https://news.ycombinator.com/item?id=46332761</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46332761</guid></item><item><title><![CDATA[New comment by dkalola in "alpr.watch"]]></title><description><![CDATA[
<p>"Systems marketed for "solving crimes" get used for immigration enforcement"<p>What immigration enforcement are you speaking of here? Legal? Illegal? If the latter, wouldn't this system be solving crime?</p>
]]></description><pubDate>Tue, 16 Dec 2025 22:14:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=46295352</link><dc:creator>dkalola</dc:creator><comments>https://news.ycombinator.com/item?id=46295352</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46295352</guid></item><item><title><![CDATA[New comment by dkalola in "Trumpcard (Official US Government Website)"]]></title><description><![CDATA[
<p>Why call it the Trump card? Regardless of what side you are on, this country is bigger than one man. This branding seems flippant and unserious.</p>
]]></description><pubDate>Sat, 20 Sep 2025 01:35:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=45309086</link><dc:creator>dkalola</dc:creator><comments>https://news.ycombinator.com/item?id=45309086</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45309086</guid></item><item><title><![CDATA[New comment by dkalola in "Pleasures by Aldous Huxley (1920)"]]></title><description><![CDATA[
<p>This essay by Huxley said exactly what I have always felt but never articulated. The problem is far worse today than it was in his time. So much of recreation today consists of binge-watching Netflix. In addition, because Netflix has global reach, the world often watches the same content, devoid of local meaning.<p>I have realized that active recreation, although requiring overcoming a certain threshold of activation energy, is far more compelling and fulfilling than passive recreation.</p>
]]></description><pubDate>Mon, 26 Feb 2024 03:40:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=39507413</link><dc:creator>dkalola</dc:creator><comments>https://news.ycombinator.com/item?id=39507413</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39507413</guid></item><item><title><![CDATA[New comment by dkalola in "I used to not worry about climate change. Now I do [video]"]]></title><description><![CDATA[
<p>The new video is pretty funny!</p>
]]></description><pubDate>Sun, 28 Jan 2024 14:19:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=39166005</link><dc:creator>dkalola</dc:creator><comments>https://news.ycombinator.com/item?id=39166005</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39166005</guid></item></channel></rss>