<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: nadetastic</title><link>https://news.ycombinator.com/user?id=nadetastic</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 10 Sep 2026 14:06:11 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=nadetastic" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by nadetastic in "The Microeconomics of Artificial Intelligence (2025)"]]></title><description><![CDATA[
<p>> Applied statistics is a
far more precise descriptor, “but no one wants to use that term, because
it’s not as sexy.”<p>This really hit me some time back when I was explaining AI to a friend. After about 10 mins of rambling about LLMs and mentioning the attention paper like I knew what I was talking about, it ended with “oh so it’s just a really advanced auto correct”</p>
]]></description><pubDate>Wed, 09 Sep 2026 01:17:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=49619492</link><dc:creator>nadetastic</dc:creator><comments>https://news.ycombinator.com/item?id=49619492</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49619492</guid></item><item><title><![CDATA[New comment by nadetastic in "AI financial advice is surprisingly good, especially if you ask right questions"]]></title><description><![CDATA[
<p>To me its felt like the LLM sort mirrors what you say to it and how you say it, to the point where I now include additional instructions to steer the model "Never mirror the user’s present diction, mood, or affect". It feels like I get a better experience but to be honest i haven't really done any benchmarking especially on newer models</p>
]]></description><pubDate>Sun, 02 Aug 2026 01:05:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=49140092</link><dc:creator>nadetastic</dc:creator><comments>https://news.ycombinator.com/item?id=49140092</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49140092</guid></item><item><title><![CDATA[New comment by nadetastic in "Tailscale didn't stop the Hugging Face intrusion"]]></title><description><![CDATA[
<p>Biggest take away here is that in the age of AI long lived credentials are no longer a valid option</p>
]]></description><pubDate>Sat, 01 Aug 2026 00:27:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=49130008</link><dc:creator>nadetastic</dc:creator><comments>https://news.ycombinator.com/item?id=49130008</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49130008</guid></item></channel></rss>