<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: jacktu</title><link>https://news.ycombinator.com/user?id=jacktu</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 09 May 2026 03:09:36 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=jacktu" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by jacktu in "AI didn't delete your database, you did"]]></title><description><![CDATA[
<p>When I was setting up the generation pipeline for my own AI project, I had to hardcode strict.</p>
]]></description><pubDate>Tue, 05 May 2026 18:18:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=48026416</link><dc:creator>jacktu</dc:creator><comments>https://news.ycombinator.com/item?id=48026416</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48026416</guid></item><item><title><![CDATA[New comment by jacktu in "Computer Use is 45x more expensive than structured APIs"]]></title><description><![CDATA[
<p>Totally agree. I’ve been building an AI visual tool recently and experimented with both approaches. The latency and c ost of generic "agentic" browser use are absolute dealbreakers for real-time consumer apps right now. Structured APIs (even just chained LLM calls with strict JSON schemas) are not only 40x cheaper, but more importantly, they are deterministic enough to actually build a stable product on top of. Computer use is an amazing demo, but structured APIs are what pay the server bills.</p>
]]></description><pubDate>Tue, 05 May 2026 18:12:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=48026333</link><dc:creator>jacktu</dc:creator><comments>https://news.ycombinator.com/item?id=48026333</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48026333</guid></item></channel></rss>