<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>Fri, 24 Jul 2026 02:36:54 +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 "Ask HN: What Are You Working On? (July 2026)"]]></title><description><![CDATA[
<p>We just launched <a href="https://www.dplyd.io" rel="nofollow">https://www.dplyd.io</a> which will do AI in a box. Small deployments of local models for law firms, healthcare, defense, etc…<p>There are many like it. This one is ours.</p>
]]></description><pubDate>Mon, 13 Jul 2026 04:00:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=48887748</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=48887748</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48887748</guid></item><item><title><![CDATA[New comment by hank2000 in "Ask HN: Who is hiring? (July 2026)"]]></title><description><![CDATA[
<p>Lunt | Databricks Eng (Solutions Architect, FDE) | Remote, US Only | Full time or full time contract | 120-140/hr (depending on exp, ~240-260 FTE)<p>I have ~10 opportunities for Databricks engineers as subcontractors to help large Databricks customers migrate to the platform. The Solutions Architect roles are heavily data-pipeline focused, and for the FDEs (Forward Deployed Engineers) want Databricks experience plus full stack experience to stand up Databricks apps for customers.<p>These opportunities vary from short to long term (though shorter term is probably ~6 months), and are full time even on contract. If that's you, drop me an email k at lunt dot co -- a PDF resume and phone number is the fastest way to proceed. Several of these need to start as soon as Aug 1.
not dot com.<p>If you're deep in Databricks, hmu.</p>
]]></description><pubDate>Tue, 07 Jul 2026 00:29:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=48812261</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=48812261</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48812261</guid></item><item><title><![CDATA[New comment by hank2000 in "Show HN: Dbmachine – the back end and front end are Claude, just the plumbing&DB"]]></title><description><![CDATA[
<p>If modern software is almost entirely just a DB with a thin backend and some kind of front end, why not have claude be all buy the DB.<p>this is a standardized back end so you can build a CRM, or an analytics engine... think a very basic local supabase, but with for claude as the whole means of interface.</p>
]]></description><pubDate>Mon, 08 Jun 2026 14:56:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=48446234</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=48446234</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48446234</guid></item><item><title><![CDATA[Show HN: dbmachine – the back end and front end are Claude, just the plumbing&DB]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/kenm47/dbmachine">https://github.com/kenm47/dbmachine</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48446233">https://news.ycombinator.com/item?id=48446233</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Mon, 08 Jun 2026 14:56:35 +0000</pubDate><link>https://github.com/kenm47/dbmachine</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=48446233</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48446233</guid></item><item><title><![CDATA[Show HN: NvEnvy – A Notational Velocity (NvAlt) Reboot in Swift. OSS]]></title><description><![CDATA[
<p>I'm a long time user of Notational Velocity and then nvAlt, and tried nvUltra recently but in the world of Claude it felt like I should own my own——change behaviors as I need them.<p>Right now it's just a Mac app, but iOS coming in the future for myself, sync with icloud. Notes are saves as .md files and have quick search. You can open the same folder with Obsidian if that's your jam (Obsidian always felt slow and clunky to me, I know folks love it though, so keeping it compatible).<p>The app is very simple, just plain text. We don't even render markdown right now, though it's coming.<p>Definitely vibe coded. Definitely will need some updates, but share it before it's polished....  PRs appreciated.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48325776">https://news.ycombinator.com/item?id=48325776</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 29 May 2026 16:48:45 +0000</pubDate><link>https://github.com/kenm47/nvEnvy</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=48325776</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48325776</guid></item><item><title><![CDATA[New comment by hank2000 in "I'm Tired of Talking to AI"]]></title><description><![CDATA[
<p>As a person running a network of CTOs that meet in person and interact very human-ly.... I agree and see the value now more than ever in human interaction.<p>(to be clear, i do a lot of things, but this is one of them, and boy is it wild how important it feels)</p>
]]></description><pubDate>Wed, 27 May 2026 16:51:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=48296961</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=48296961</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48296961</guid></item><item><title><![CDATA[New comment by hank2000 in "Fecal transplants for autism deliver success in clinical trials (2019)"]]></title><description><![CDATA[
<p>The number of stories I’ve read in the last 15 years that amount to: “desperate after years of trying everything, we bought a blender and ground up my wife’s shit and put it up my butt, and within a 24 hours I was totally fine”<p>Is kind of impressive.</p>
]]></description><pubDate>Sat, 16 May 2026 13:46:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=48160237</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=48160237</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48160237</guid></item><item><title><![CDATA[New comment by hank2000 in "Googlebook"]]></title><description><![CDATA[
<p>Is this what happens when you let Gemini name your products?</p>
]]></description><pubDate>Wed, 13 May 2026 04:11:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=48117711</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=48117711</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48117711</guid></item><item><title><![CDATA[New comment by hank2000 in "UCLA discovers first stroke rehabilitation drug to repair brain damage (2025)"]]></title><description><![CDATA[
<p>My understanding was that psychedelics have proven to be effective at opening up a “critical period” where a brain can rewire itself like when in childhood. Wonder if this is related.<p><a href="https://academic.oup.com/brain/article/148/6/1862/8052899?guestAccessKey=" rel="nofollow">https://academic.oup.com/brain/article/148/6/1862/8052899?gu...</a></p>
]]></description><pubDate>Tue, 12 May 2026 01:50:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=48103240</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=48103240</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48103240</guid></item><item><title><![CDATA[New comment by hank2000 in "GPT‑5.5 Instant"]]></title><description><![CDATA[
<p>Yall want to see instant? Check out chatjimmy.ai blow your mind.  I’m not affiliated.<p>But the things it unlocks in a product I’m building are mind blowing. Millisecond inference even on much older models will change the whole game. Enough to run inference on every. Single. API call. Without notable disruption. This sh*t is wild.</p>
]]></description><pubDate>Wed, 06 May 2026 01:17:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=48030985</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=48030985</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48030985</guid></item><item><title><![CDATA[New comment by hank2000 in "Meetings are forcing functions"]]></title><description><![CDATA[
<p>Engineers: All a meeting does is distract from work.<p>Every leader ever: if we could do the right work, we could have less meetings.<p>I agree with the sentiment. And also understand the rage you’ll get.</p>
]]></description><pubDate>Tue, 28 Apr 2026 00:51:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=47929191</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=47929191</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47929191</guid></item><item><title><![CDATA[New comment by hank2000 in "Claude Code removed from Anthropic's Pro plan"]]></title><description><![CDATA[
<p>how was it? I'm doing this today</p>
]]></description><pubDate>Tue, 21 Apr 2026 22:14:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=47855309</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=47855309</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47855309</guid></item><item><title><![CDATA[New comment by hank2000 in "GPU Breach: A Root Shell Through GPU Abuse"]]></title><description><![CDATA[
<p>The University of Toronto research team, led by Chris S. Lin and Prof. Gururaj Saileshwar recently disclosed GPUBreach (<a href="https://gpubreach.ca" rel="nofollow">https://gpubreach.ca</a>) a new class of attack targeting NVIDIA GPU drivers. The work highlights how fault injection techniques such as Rowhammer can be combined with GPU memory management behavior to achieve privilege escalation, even in environments with protections like the IOMMU enabled.<p>This article is about how we, at Stealthium, reverse engineered what was going on and explain this new kind of attack.</p>
]]></description><pubDate>Thu, 16 Apr 2026 13:17:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=47792542</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=47792542</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47792542</guid></item><item><title><![CDATA[GPU Breach: A Root Shell Through GPU Abuse]]></title><description><![CDATA[
<p>Article URL: <a href="https://stealthium.io/blog/gpubreach-root-cause-analysis-detection">https://stealthium.io/blog/gpubreach-root-cause-analysis-detection</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47792541">https://news.ycombinator.com/item?id=47792541</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Thu, 16 Apr 2026 13:17:51 +0000</pubDate><link>https://stealthium.io/blog/gpubreach-root-cause-analysis-detection</link><dc:creator>hank2000</dc:creator><comments>https://news.ycombinator.com/item?id=47792541</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47792541</guid></item><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></channel></rss>