<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: thekracken</title><link>https://news.ycombinator.com/user?id=thekracken</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 13 Jul 2026 07:26:27 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=thekracken" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by thekracken in "HN Slop: AI startup ideas generated from Hacker News"]]></title><description><![CDATA[
<p>><i>SciShow are stricter than any academic journal I've published in</i><p>Now there's a testimonial. I look forward to browsing the source links with each video!</p>
]]></description><pubDate>Wed, 02 Jul 2025 07:21:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=44441003</link><dc:creator>thekracken</dc:creator><comments>https://news.ycombinator.com/item?id=44441003</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44441003</guid></item><item><title><![CDATA[New comment by thekracken in "HN Slop: AI startup ideas generated from Hacker News"]]></title><description><![CDATA[
<p>><i>I've experimented with every SOTA model since 2022</i><p>><i>The content is usually reasonably strong but the tone is always off and it never quite understands what it is a reader/viewer needs</i><p>A SOTA model fine-tuned with your choice of transcripts could probably get you most of the way there. There might be a customized, open-weight model already on Huggingface that meets your needs.</p>
]]></description><pubDate>Wed, 02 Jul 2025 07:16:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=44440986</link><dc:creator>thekracken</dc:creator><comments>https://news.ycombinator.com/item?id=44440986</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44440986</guid></item></channel></rss>