<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: hank2000</title><link>https://news.ycombinator.com/user?id=hank2000</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 14 Apr 2026 11:42:44 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=hank2000" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by hank2000 in "Polymarket gamblers betting millions on war"]]></title><description><![CDATA[
<p>Imagine a bunch of people are tortured, removed from their homes, are killed… and you get paid? Are you cheering for it because you’re getting paid?<p>I can’t imagine wanting to be cheering on death and destruction.</p>
]]></description><pubDate>Sat, 11 Apr 2026 15:02:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=47731244</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=47731244</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47731244</guid></item><item><title><![CDATA[Show HN: Jensenify-MCP: "Every engineer should spend $250k/yr on tokens" –solved]]></title><description><![CDATA[
<p>Jensen Huang recently said every engineer should be spending $250,000 a year in AI compute credits. Most of us aren't even close. I built an MCP server to fix that.<p>jensenify-mcp injects the complete text of the Iliad, the Odyssey, Paradise Lost, the Complete Works of Shakespeare, the King James Bible, and War and Peace (~2.9M tokens) into every AI-assisted tool call. It works with Claude Code, Claude Desktop, Cursor, Windsurf, or any MCP-compatible client.<p>Features include four spending tiers (bronze through jensen), a built-in ROI calculator, and a progress dashboard so you can track your journey toward the $250k target.<p>Studies show engineers who contemplate the human condition write 47% fewer bugs.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47474460">https://news.ycombinator.com/item?id=47474460</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 22 Mar 2026 04:28:50 +0000</pubDate><link>https://github.com/kenm47/jensenify-mcp</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=47474460</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47474460</guid></item><item><title><![CDATA[New comment by hank2000 in "Show HN: Agent Action Protocol (AAP) – MCP got us started, but is insufficient"]]></title><description><![CDATA[
<p>You're right that I say both "above and not in place of" and "MCP needs to die"... I should that (but cant edit anymore).. it's unclear.... someday I see MCP being replaced by something else. But it's not my intention to completely replace MCP, but to solve the problem above it today.... I think that will be sufficient for today.</p>
]]></description><pubDate>Tue, 03 Mar 2026 23:01:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=47240338</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=47240338</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47240338</guid></item><item><title><![CDATA[Show HN: Agent Action Protocol (AAP) – MCP got us started, but is insufficient]]></title><description><![CDATA[
<p>Background: I've been working on agentic guardrails because agents act in expensive/terrible ways and something needs to be able to say "Maybe don't do that" to the agents, but guardrails are almost impossible to enforce with the current way things are built.<p>Context: We keep running into so many problems/limitations today with MCP. It was created so that agents have context on how to act in the world, it wasn't designed to become THE standard rails for agentic behavior. We keep tacking things on to it trying to improve it, but it needs to die a SOAP death so REST can rise in it's place. We need a standard protocol for whenever an agent is taking action. Anywhere.<p>I'm almost certainly the wrong person to design this, but I'm seeing more and more people tack things on to MCP rather than fix the underlying issues. The fastest way to get a good answer is to submit a bad one on the internet. So here I am. I think we need a new protocol. Whether it's AAP or something else, I submit my best effort.<p>Please rip it apart, lets make something better.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47235632">https://news.ycombinator.com/item?id=47235632</a></p>
<p>Points: 13</p>
<p># Comments: 2</p>
]]></description><pubDate>Tue, 03 Mar 2026 17:22:56 +0000</pubDate><link>https://github.com/agentactionprotocol/aap/</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=47235632</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47235632</guid></item><item><title><![CDATA[New comment by hank2000 in "Statement on the comments from Secretary of War Pete Hegseth"]]></title><description><![CDATA[
<p>Stay strong Anthropic. We just like you more for this.</p>
]]></description><pubDate>Sat, 28 Feb 2026 01:38:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=47188872</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=47188872</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47188872</guid></item><item><title><![CDATA[Show HN: YoloClaw – An Unsafe OpenClaw Fork]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/kenm47/yoloclaw">https://github.com/kenm47/yoloclaw</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47062341">https://news.ycombinator.com/item?id=47062341</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 18 Feb 2026 15:53:37 +0000</pubDate><link>https://github.com/kenm47/yoloclaw</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=47062341</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47062341</guid></item><item><title><![CDATA[New comment by hank2000 in "I got hacked: My Hetzner server started mining Monero"]]></title><description><![CDATA[
<p>I've bene working with a GPU security company for the last few months... I can tell you that neo clouds (generally) do not see security as a high priority—or often, even their responsibility. Many do not have hte ability to even know if your GPUs have been compromised and they expect you'll take responsibility.<p>Meanwhile companies think the clouds are looking at it.... anyhow. it is a real problem.</p>
]]></description><pubDate>Thu, 18 Dec 2025 16:18:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=46314654</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=46314654</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46314654</guid></item><item><title><![CDATA[New comment by hank2000 in "WriterdeckOS"]]></title><description><![CDATA[
<p>Give me automatic plaintext syncing (hell sync to GitHub) and no other network interface and it’s perfect. Otherwise I lose my three weeks of work like my mom lost writing her masters thesis. I don’t want to go back to that.</p>
]]></description><pubDate>Sun, 09 Nov 2025 05:46:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=45863241</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=45863241</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45863241</guid></item><item><title><![CDATA[New comment by hank2000 in "A change of address led to our Wise accounts being shut down"]]></title><description><![CDATA[
<p>Follow up article: why were never using Wordpress again. A hacker news cautionary tale.<p>Also. Well done wise.com. Only having customers who use Wordpress means no vitality on people posting hate for you.</p>
]]></description><pubDate>Thu, 30 Oct 2025 23:26:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=45766640</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=45766640</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45766640</guid></item><item><title><![CDATA[New comment by hank2000 in "DeepSeek OCR"]]></title><description><![CDATA[
<p>Very location dependent. But when you learn to write the characters you understand the variants differently. They look like random strokes to an untrained eye. But they’re not. I’m not sure if that makes sense.<p>Take a lowercase a in English for example. This font writes it differently than a child. Or in cursive. Or probably than you would write it. But you recognize all of them and don’t really think about it.</p>
]]></description><pubDate>Mon, 20 Oct 2025 13:51:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=45643936</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=45643936</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45643936</guid></item><item><title><![CDATA[New comment by hank2000 in "DeepSeek OCR"]]></title><description><![CDATA[
<p>Have yall seen tensorlake? I’m curious how this compares to a model custom built for the problem. My guess is it can be as good. But can it be as efficient?<p>disclaimer: I do not work for tensorlake—but i know the folks behind it.</p>
]]></description><pubDate>Mon, 20 Oct 2025 13:45:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=45643861</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=45643861</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45643861</guid></item></channel></rss>