<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: d4lt4</title><link>https://news.ycombinator.com/user?id=d4lt4</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sun, 31 May 2026 18:15:09 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=d4lt4" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by d4lt4 in "Thoughts on slowing the fuck down"]]></title><description><![CDATA[
<p>There is a paper [0] that shows that LLMs, in fact, cannot write and modify ‘whatever’ pretty well.<p>[0] A Survey on Large Language Models for Code Generation: <a href="https://dl.acm.org/doi/epdf/10.1145/3747588" rel="nofollow">https://dl.acm.org/doi/epdf/10.1145/3747588</a></p>
]]></description><pubDate>Thu, 26 Mar 2026 04:36:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=47526679</link><dc:creator>d4lt4</dc:creator><comments>https://news.ycombinator.com/item?id=47526679</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47526679</guid></item></channel></rss>