<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: neurworlds</title><link>https://news.ycombinator.com/user?id=neurworlds</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 07 Apr 2026 01:35:14 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=neurworlds" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by neurworlds in "Show HN: Modo – I built an open-source alternative to Kiro, Cursor, and Windsurf"]]></title><description><![CDATA[
<p>curious how Modo handles multi-file edits across a monorepo, that's where most tools fall apart for me</p>
]]></description><pubDate>Mon, 06 Apr 2026 13:21:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=47660569</link><dc:creator>neurworlds</dc:creator><comments>https://news.ycombinator.com/item?id=47660569</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47660569</guid></item><item><title><![CDATA[New comment by neurworlds in "The 1987 game “The Last Ninja” was 40 kilobytes"]]></title><description><![CDATA[
<p>40kb and it felt like a full world... I'm burning through tokens to get AI to decide whether to go to the tavern or the market. Something went wrong somewhere</p>
]]></description><pubDate>Mon, 06 Apr 2026 13:20:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=47660551</link><dc:creator>neurworlds</dc:creator><comments>https://news.ycombinator.com/item?id=47660551</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47660551</guid></item><item><title><![CDATA[New comment by neurworlds in "Show HN: I built a tiny LLM to demystify how language models work"]]></title><description><![CDATA[
<p>Cool project. I'm working on something where multiple LLM agents share a world and interact with each other autonomously. One thing that surprised me is how much the "world" matters — same model, same prompt, but put it in a system with resource constraints, other agents, and persistent memory, the behavior changes dramatically. Made me realize we spend too much time optimizing the model and not enough thinking about the environment it operates in.</p>
]]></description><pubDate>Mon, 06 Apr 2026 13:16:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=47660517</link><dc:creator>neurworlds</dc:creator><comments>https://news.ycombinator.com/item?id=47660517</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47660517</guid></item></channel></rss>