<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: iceman28</title><link>https://news.ycombinator.com/user?id=iceman28</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 11 Apr 2026 17:40:47 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=iceman28" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by iceman28 in "20 years on AWS and never not my job"]]></title><description><![CDATA[
<p>It was a different time when software was seen as something that was built together and everyone was interested in learning the best from one another.</p>
]]></description><pubDate>Sat, 11 Apr 2026 07:23:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=47728328</link><dc:creator>iceman28</dc:creator><comments>https://news.ycombinator.com/item?id=47728328</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47728328</guid></item><item><title><![CDATA[New comment by iceman28 in "Project Vend: Phase Two"]]></title><description><![CDATA[
<p>Really fun read. To be this seems awful close to my experience using these models to code. When the prompts are simple and direct to follow the models do really good. Once the context overflows and you repopulate it, they start to hallucinate and it becomes very hard to bring them back from that.<p>It’s also good to see Anthropic being honest that models are still quite a long way away from being completely independently and providing a way to independently run business on their own.</p>
]]></description><pubDate>Sun, 28 Dec 2025 08:59:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=46409553</link><dc:creator>iceman28</dc:creator><comments>https://news.ycombinator.com/item?id=46409553</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46409553</guid></item></channel></rss>