<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: Rohinator</title><link>https://news.ycombinator.com/user?id=Rohinator</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 14 Apr 2026 16:43:28 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=Rohinator" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by Rohinator in "AI will never be ethical or safe"]]></title><description><![CDATA[
<p>Would AI be safer or more ethical if it required malicious users to lie about their intent first?<p>"Most people don’t provide their context. They never have—not to search engines, not to librarians, not to hardware store clerks."<p>Exactly. Are hardware store clerks unethical as well?</p>
]]></description><pubDate>Tue, 14 Apr 2026 15:51:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=47767263</link><dc:creator>Rohinator</dc:creator><comments>https://news.ycombinator.com/item?id=47767263</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47767263</guid></item><item><title><![CDATA[New comment by Rohinator in "Tax Wrapped 2025"]]></title><description><![CDATA[
<p>Love this - hoping this goes viral and people actually start talking about the deficit</p>
]]></description><pubDate>Mon, 13 Apr 2026 22:28:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=47758774</link><dc:creator>Rohinator</dc:creator><comments>https://news.ycombinator.com/item?id=47758774</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47758774</guid></item><item><title><![CDATA[New comment by Rohinator in "Ask HN: What Are You Working On? (April 2026)"]]></title><description><![CDATA[
<p>I'm working on some free financial planning tools at:  <a href="https://financialwebtools.com/" rel="nofollow">https://financialwebtools.com/</a><p>I found that most tools online are either overly simplistic, non-responsive, and/or require you to hand over a bunch of contact information before getting results. I built snappy web tools for retirement planning, budgeting, debt paydown, house hacking, etc. that show you quickly and visually how changing variables like interest rates, savings rates, inflation, etc. impact your financial positioning.</p>
]]></description><pubDate>Mon, 13 Apr 2026 22:24:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=47758731</link><dc:creator>Rohinator</dc:creator><comments>https://news.ycombinator.com/item?id=47758731</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47758731</guid></item><item><title><![CDATA[New comment by Rohinator in "The trust-latency gap: why the future of UX is intentionally slower"]]></title><description><![CDATA[
<p>This is personally fascinating because I've been working on financial modeling tools that are intentionally very snappy. The idea being that if users can immediately see how changing variables like interest rates impact their projections, they can get a better sense for how these variables behave. My models don't make any decisions on behalf of the user though, so they probably fall into the "reversible, low impact" camp.<p>It does feel like this prescription for strategic latency for important actions will only decay in value with time, though. Today people expect latency for important actions because historically that's been the case. But as people get more accustomed to AI and faster compute, I imagine programming in strategic latency will become less and less wise.</p>
]]></description><pubDate>Mon, 13 Apr 2026 22:13:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=47758598</link><dc:creator>Rohinator</dc:creator><comments>https://news.ycombinator.com/item?id=47758598</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47758598</guid></item><item><title><![CDATA[New comment by Rohinator in "Claude is getting worse, according to Claude"]]></title><description><![CDATA[
<p>Using Claude as a benchmark for its own quality is pretty funny. If we think the quality has declined, wouldn't that also apply to the benchmarking process itself?</p>
]]></description><pubDate>Mon, 13 Apr 2026 22:02:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=47758452</link><dc:creator>Rohinator</dc:creator><comments>https://news.ycombinator.com/item?id=47758452</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47758452</guid></item><item><title><![CDATA[New comment by Rohinator in "N-Day-Bench – Can LLMs find real vulnerabilities in real codebases?"]]></title><description><![CDATA[
<p>Very curious how Claude Mythos will perform here</p>
]]></description><pubDate>Mon, 13 Apr 2026 21:59:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=47758417</link><dc:creator>Rohinator</dc:creator><comments>https://news.ycombinator.com/item?id=47758417</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47758417</guid></item></channel></rss>