<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: rupertsworld</title><link>https://news.ycombinator.com/user?id=rupertsworld</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 30 Jul 2026 10:16:55 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=rupertsworld" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by rupertsworld in "MCP 2026-07-28 Specification: transport going stateless"]]></title><description><![CDATA[
<p>I'm currently working on getting all my MCP tools ported over to HTTP, with a single call_http tool, so I can just call APIs and benefit from a long history of patterns (like stateless-ness) that have already existed there for decades.</p>
]]></description><pubDate>Tue, 28 Jul 2026 23:41:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=49091511</link><dc:creator>rupertsworld</dc:creator><comments>https://news.ycombinator.com/item?id=49091511</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49091511</guid></item><item><title><![CDATA[New comment by rupertsworld in "So where are all the AI apps?"]]></title><description><![CDATA[
<p>One problem with a lot of the skepticism around AI produced software is that it focuses on <i>existing</i> ways of packaging and delivering software. PyPi packages are one example, shipping “apps” another.<p>While it’s interesting to see that in open source software the increase is not dramatic, this ignores however many people are now gen-coding software they will never publish just for them, or which winds up on hosting platforms like Replit.</p>
]]></description><pubDate>Tue, 24 Mar 2026 16:12:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=47504900</link><dc:creator>rupertsworld</dc:creator><comments>https://news.ycombinator.com/item?id=47504900</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47504900</guid></item><item><title><![CDATA[WebMCP Proposal]]></title><description><![CDATA[
<p>Article URL: <a href="https://webmachinelearning.github.io/webmcp/">https://webmachinelearning.github.io/webmcp/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47027299">https://news.ycombinator.com/item?id=47027299</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 15 Feb 2026 20:37:49 +0000</pubDate><link>https://webmachinelearning.github.io/webmcp/</link><dc:creator>rupertsworld</dc:creator><comments>https://news.ycombinator.com/item?id=47027299</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47027299</guid></item><item><title><![CDATA[New comment by rupertsworld in "Show HN: Generate Web Interfaces from Data"]]></title><description><![CDATA[
<p>Generative UI has a lot of potential, and some of the ideas here are interesting, but the positioning as a developer tool (for folks that can just generate stable UI using claude code already) seems odd to me. What's the expected use case?<p>I'm interested in exploring the ideas here for on-the-fly output based on user intent. It reminds me a bit of the schema model I used for the LangView experimental library (<a href="https://x.com/rupertmanfredi/status/1653780093712633859" rel="nofollow">https://x.com/rupertmanfredi/status/1653780093712633859</a>).</p>
]]></description><pubDate>Fri, 13 Feb 2026 01:09:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=46997653</link><dc:creator>rupertsworld</dc:creator><comments>https://news.ycombinator.com/item?id=46997653</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46997653</guid></item></channel></rss>