<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: andrewjvb</title><link>https://news.ycombinator.com/user?id=andrewjvb</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sun, 26 Apr 2026 09:54:36 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=andrewjvb" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by andrewjvb in "I Cancelled Claude: Token Issues, Declining Quality, and Poor Support"]]></title><description><![CDATA[
<p>It's a good point. To me this really comes down to the economics of the software being written.<p>If it's low-stakes, then the required depth to accept the code is also low.</p>
]]></description><pubDate>Fri, 24 Apr 2026 18:34:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=47894138</link><dc:creator>andrewjvb</dc:creator><comments>https://news.ycombinator.com/item?id=47894138</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47894138</guid></item><item><title><![CDATA[New comment by andrewjvb in "Changes to GitHub Copilot individual plans"]]></title><description><![CDATA[
<p>Been having a ton of fun with copilot cli directed to local qwen 3.6. If you’re willing to increase the amount of specificity in your prompts then delegating from a GPT-5.4 or Opus to local qwen has been great so far.</p>
]]></description><pubDate>Wed, 22 Apr 2026 01:49:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=47857723</link><dc:creator>andrewjvb</dc:creator><comments>https://news.ycombinator.com/item?id=47857723</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47857723</guid></item></channel></rss>