<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
	<channel>
		<title>Ideas on Nishanth Sudharsanam</title>
		<link>https://nishanth.blog/ideas/</link>
		<description>Recent content in Ideas on Nishanth Sudharsanam</description>
		<generator>Hugo</generator>
		<language>en-us</language>
		
		
		
		
			<lastBuildDate>Fri, 16 Oct 2026 12:00:00 +0800</lastBuildDate>
		
			<atom:link href="https://nishanth.blog/ideas/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>Arguing the idea with a reader</title>
				<link>https://nishanth.blog/ideas/arguing-the-idea-with-a-reader/</link>
				<pubDate>Fri, 16 Oct 2026 12:00:00 +0800</pubDate>
				<guid>https://nishanth.blog/ideas/arguing-the-idea-with-a-reader/</guid>
				<description>&lt;p&gt;In an attempt to help Claude frame a write-up, I had it argue the crux of the post with an imagined skeptical reader, a backend engineer who thinks AI writing is bad because the models aren&amp;rsquo;t good enough yet. The entire conversation below was generated by Claude and I found it surprisingly engaging to read, much more than the article derived from it afterwards. So I am posting it here for reference.&lt;/p&gt;</description>
			</item>
	</channel>
</rss>
