<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: jelmersnoeck</title><link>https://news.ycombinator.com/user?id=jelmersnoeck</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sun, 24 May 2026 20:00:32 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=jelmersnoeck" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by jelmersnoeck in "-​-dangerously-skip-reading-code"]]></title><description><![CDATA[
<p>> "I'd make a standardized Markdown specification the new unit of knowledge for the software project. ... There would need to be automated pull-request checks verifying not only that tests pass but that code conforms to the spec."<p>Agree, this is how you make the development loop more deterministic and ultimately autonomous. It's how I've been using coding agents myself for the past few months (by building my own to support this natively [1]).<p>If you have a spec you approve/agree on, have an agent code against it, and then have a review phase verify the implementation didn't drift from the spec (either by adding or removing features), you get to a position where you can trust the outcome.<p>There's still a lot to be said about spec definition and what if during implementation gaps are discovered, and that's where HITL comes into play.<p>[1] <a href="https://github.com/jelmersnoeck/forge" rel="nofollow">https://github.com/jelmersnoeck/forge</a></p>
]]></description><pubDate>Sun, 24 May 2026 03:34:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=48254109</link><dc:creator>jelmersnoeck</dc:creator><comments>https://news.ycombinator.com/item?id=48254109</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48254109</guid></item><item><title><![CDATA[Agents Are Not One Thing]]></title><description><![CDATA[
<p>Article URL: <a href="https://jlmr.dev/posts/agents-are-not-one-thing/">https://jlmr.dev/posts/agents-are-not-one-thing/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48225607">https://news.ycombinator.com/item?id=48225607</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 21 May 2026 16:43:06 +0000</pubDate><link>https://jlmr.dev/posts/agents-are-not-one-thing/</link><dc:creator>jelmersnoeck</dc:creator><comments>https://news.ycombinator.com/item?id=48225607</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48225607</guid></item><item><title><![CDATA[New comment by jelmersnoeck in "Your app subscription is now my weekend project"]]></title><description><![CDATA[
<p>I like this approach, at least for personal apps. I have started doing this myself, which also led into me learning to use LLMs better and more productively.<p>The other side of the coin however is a potential decline in indie hacker products.</p>
]]></description><pubDate>Fri, 23 Jan 2026 00:52:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=46727039</link><dc:creator>jelmersnoeck</dc:creator><comments>https://news.ycombinator.com/item?id=46727039</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46727039</guid></item></channel></rss>