<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: drewvlaz</title><link>https://news.ycombinator.com/user?id=drewvlaz</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 16 Apr 2026 19:13:29 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=drewvlaz" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by drewvlaz in "We pwned X, Vercel, Cursor, and Discord through a supply-chain attack"]]></title><description><![CDATA[
<p>Wow did not realize a url could be set like that without promoting a page reload...</p>
]]></description><pubDate>Fri, 19 Dec 2025 00:03:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=46320610</link><dc:creator>drewvlaz</dc:creator><comments>https://news.ycombinator.com/item?id=46320610</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46320610</guid></item><item><title><![CDATA[New comment by drewvlaz in "How Anthropic teams use Claude Code"]]></title><description><![CDATA[
<p>One really has to wonder what their actual margins are though, considering the Claude Code plans vs API pricing</p>
]]></description><pubDate>Fri, 25 Jul 2025 03:37:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=44679350</link><dc:creator>drewvlaz</dc:creator><comments>https://news.ycombinator.com/item?id=44679350</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44679350</guid></item><item><title><![CDATA[New comment by drewvlaz in "It's rude to show AI output to people"]]></title><description><![CDATA[
<p>One of the largest issues I've experienced is LLMs being too agreeable.<p>I don't want my theories parroted back to me on why something went wrong. I want to have ideas challenged in a way that forces me to think and hopefully lead me to a new perspective that I otherwise would have missed.<p>Perhaps a large portion of people do enjoy the agreeableness, but this becomes a problem not only because I think there are larger societal issues that stem from this echo-chamber like environmental but also simply that companies training these models may interpret agreeableness as somehow better and something that should be optimized for.</p>
]]></description><pubDate>Sat, 19 Jul 2025 17:47:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=44617636</link><dc:creator>drewvlaz</dc:creator><comments>https://news.ycombinator.com/item?id=44617636</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44617636</guid></item><item><title><![CDATA[New comment by drewvlaz in "Show HN: Unsure Calculator – back-of-a-napkin probabilistic calculator"]]></title><description><![CDATA[
<p>This was quite a fun read, thanks!</p>
]]></description><pubDate>Wed, 16 Apr 2025 01:08:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=43700286</link><dc:creator>drewvlaz</dc:creator><comments>https://news.ycombinator.com/item?id=43700286</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43700286</guid></item></channel></rss>