<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: MndlshnDscpl</title><link>https://news.ycombinator.com/user?id=MndlshnDscpl</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 07 Apr 2026 23:03:11 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=MndlshnDscpl" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by MndlshnDscpl in "A Software Development Methodology for Disciplined LLM Collaboration"]]></title><description><![CDATA[
<p>Agreed 100%. For those of us who have already spent ungodly hours creating hyper-detailed specifications for AI, the take that this is the solution to working with AI coding agents seems ridiculously naive. For context, I've also seen this behavior in Claude Code, and despite initially being extremely bullish on the technology, it's almost convinced me that it just isn't ready for prime time no matter what the hucksters might tell you. When you start seeing this you quickly realize that it doesn't really matter how many guardrails you put in place, or how detailed your specification is, if your coding agent randomly decides to ignore your rules or specifications(even in 'brand new context' scenarios). I've lost track of how many times I've asked Claude why did you do this, when it expressly says to do the opposite in the Claude.md file(including words like 'important' or 'critical'), or a specification document that you <i>read right before implementing with a brand new context</i>. Naturally, Claude's reply will be some variation of 'You're absolutely right to call me out on this. I should have done it the way it was spelled out in the specification.'</p>
]]></description><pubDate>Sun, 07 Sep 2025 11:43:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=45157345</link><dc:creator>MndlshnDscpl</dc:creator><comments>https://news.ycombinator.com/item?id=45157345</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45157345</guid></item><item><title><![CDATA[New comment by MndlshnDscpl in "OpenAI’s board, paraphrased: ‘All we need is unimaginable sums of money’"]]></title><description><![CDATA[
<p>Agreed. I think originally, it would have been more accurate to say IE was based on Mosaic. If I recall correctly, I think Microsoft bought out Spyglass Mosaic to base IE on, and that browser <i>had</i> been licensed from the NCSA. Netscape on the other hand had originally been Mosaic Communications(anyone remember home.mcom.com?) and changed the name when they did the clean rewrite. I think the name Mozilla came about because they were looking for a 'Mosaic Killer' or something along those lines. Memories are kind of fuzzy so I'm sure someone on here has a better recollection.</p>
]]></description><pubDate>Mon, 30 Dec 2024 00:02:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=42544827</link><dc:creator>MndlshnDscpl</dc:creator><comments>https://news.ycombinator.com/item?id=42544827</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42544827</guid></item><item><title><![CDATA[New comment by MndlshnDscpl in "More men are addicted to the 'crack cocaine' of the stock market"]]></title><description><![CDATA[
<p>This is a famous misattribution typically used to state generational views have always been the same. Unfortunately its not Socrates, but actually Kenneth Freeman, Cambridge, 1907.</p>
]]></description><pubDate>Wed, 25 Dec 2024 00:20:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=42505955</link><dc:creator>MndlshnDscpl</dc:creator><comments>https://news.ycombinator.com/item?id=42505955</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42505955</guid></item></channel></rss>