<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: psma_egeliaa</title><link>https://news.ycombinator.com/user?id=psma_egeliaa</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 22 Aug 2026 02:22:31 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=psma_egeliaa" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by psma_egeliaa in "AI companies destroy physical books – let's scan rare books before it's too late"]]></title><description><![CDATA[
<p>It will probably be actioned off in the bankruptcy proceedings.</p>
]]></description><pubDate>Fri, 21 Aug 2026 12:33:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=49387146</link><dc:creator>psma_egeliaa</dc:creator><comments>https://news.ycombinator.com/item?id=49387146</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49387146</guid></item><item><title><![CDATA[New comment by psma_egeliaa in "Vomit: Clean up Claude 5's token output with a separate LLM"]]></title><description><![CDATA[
<p>Yeah I don't the problem is verbosity as such, as I frequently have to ask to explain how it reached a certain conclusion and in particular what the empirical evidence for it is, at which point it too frequently reconsiders its answer.<p>It's just that the details it parrots are often irrelevant and wrapped in a way that makes them seem relevant.</p>
]]></description><pubDate>Fri, 21 Aug 2026 12:31:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=49387120</link><dc:creator>psma_egeliaa</dc:creator><comments>https://news.ycombinator.com/item?id=49387120</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49387120</guid></item></channel></rss>