<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: tryall</title><link>https://news.ycombinator.com/user?id=tryall</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 30 Apr 2026 20:32:03 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=tryall" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by tryall in "Vera: a programming language designed for machines to write"]]></title><description><![CDATA[
<p>The FAQ says shuffled names (renaming a variable 'count' to 'result') make LLM perform poorly. But I never seen any codebase have this kind of lies (except from comments). And LLM writing code almost never do that.<p>Seems like a weird decision taken from a weird paper that make everything harder for humans AND llms. Variables names give useful context when correctly named.</p>
]]></description><pubDate>Thu, 30 Apr 2026 15:02:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=47963594</link><dc:creator>tryall</dc:creator><comments>https://news.ycombinator.com/item?id=47963594</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47963594</guid></item></channel></rss>