<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: seamlessdev</title><link>https://news.ycombinator.com/user?id=seamlessdev</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 13 Aug 2026 21:54:05 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=seamlessdev" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by seamlessdev in "Choosing an AI model: one prompt, 11 models, different results"]]></title><description><![CDATA[
<p>Definitely. It was already a trend before LLMs exploded. And the whole "all websites look the same" has been a thing since at least Bootstrap times.</p>
]]></description><pubDate>Thu, 13 Aug 2026 14:11:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=49286267</link><dc:creator>seamlessdev</dc:creator><comments>https://news.ycombinator.com/item?id=49286267</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49286267</guid></item><item><title><![CDATA[New comment by seamlessdev in "As AI eats the web, the internet’s collective memory is disappearing"]]></title><description><![CDATA[
<p>I was talking about style and architecture. In all these cases the code is working as intended either way. There is no such thing as "correct" style and architecture. There are only tradeoffs. You should know that if you have 31 years of experience.</p>
]]></description><pubDate>Tue, 11 Aug 2026 13:04:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=49257657</link><dc:creator>seamlessdev</dc:creator><comments>https://news.ycombinator.com/item?id=49257657</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49257657</guid></item><item><title><![CDATA[New comment by seamlessdev in "As AI eats the web, the internet’s collective memory is disappearing"]]></title><description><![CDATA[
<p>Yeah if you just let it run wild, it will produce subpar results. But that is not much different from humans tbh.<p>When you discuss design and architecture first, and write that out in a design doc or something along those lines, it works quite well for the most part.<p>And 9 out of 10 times when it produces some poor results, just asking "is this really a good approach?" or just stating "This code makes me very sad" it will most of the time do a really good job of analysing why that code is bad and how to improve it.</p>
]]></description><pubDate>Tue, 11 Aug 2026 12:11:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=49257005</link><dc:creator>seamlessdev</dc:creator><comments>https://news.ycombinator.com/item?id=49257005</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49257005</guid></item><item><title><![CDATA[New comment by seamlessdev in "How Claude marks AI-generated content"]]></title><description><![CDATA[
<p>Belt, braces, and suspenders.</p>
]]></description><pubDate>Mon, 10 Aug 2026 22:25:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=49250716</link><dc:creator>seamlessdev</dc:creator><comments>https://news.ycombinator.com/item?id=49250716</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49250716</guid></item></channel></rss>