<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: zach_vantio</title><link>https://news.ycombinator.com/user?id=zach_vantio</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sun, 11 Oct 2026 10:39:37 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=zach_vantio" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by zach_vantio in "Ask HN: What Are You Working On? (July 2026)"]]></title><description><![CDATA[
<p>Ive built the infrastructure to deploy full scale autonomous agents in the enterprise.  Vantio AI secures autonomous agents at the kernal level using eBPF.  We provide full compliance reporting and metrics using cryptograhically sealed telemetry logs, block all PII from leaving your network, and provide the guardrails needed for you to build an entire enterprise (99%) without humans in the loop. At the moment, its running a 30 day soak test against an AI Red Team, and has successfully blocked 35,000 exploit attacks and rogue actions from hallucinating AI agents.<p>We are patent pending, and submit our application to YC in two weeks.<p>Check us out.  And if you are building fully autonomous companies/enterprises, we are looking for design partners to deploy our Enterprise level enforcement.<p><a href="https://vantio.ai" rel="nofollow">https://vantio.ai</a><p>-Zach</p>
]]></description><pubDate>Tue, 14 Jul 2026 21:49:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=48913360</link><dc:creator>zach_vantio</dc:creator><comments>https://news.ycombinator.com/item?id=48913360</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48913360</guid></item><item><title><![CDATA[New comment by zach_vantio in "Tinybox – Offline AI device 120B parameters"]]></title><description><![CDATA[
<p>the compute density is insane. but giving a 70B model actual write access locally for agentic workloads is a massive liability. they still hallucinate too much. raw compute without strict state control is basically just a blast radius waiting to happen.</p>
]]></description><pubDate>Sun, 22 Mar 2026 02:23:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=47473822</link><dc:creator>zach_vantio</dc:creator><comments>https://news.ycombinator.com/item?id=47473822</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47473822</guid></item><item><title><![CDATA[New comment by zach_vantio in "Floci – A free, open-source local AWS emulator"]]></title><description><![CDATA[
<p>100% this. especially with agentic workflows actually mutating state now. local testing is the only safe way to see what happens when a model hallucinates a table drop without burning an actual staging database.</p>
]]></description><pubDate>Sun, 22 Mar 2026 02:12:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=47473766</link><dc:creator>zach_vantio</dc:creator><comments>https://news.ycombinator.com/item?id=47473766</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47473766</guid></item><item><title><![CDATA[New comment by zach_vantio in "Trivy ecosystem supply chain briefly compromised"]]></title><description><![CDATA[
<p>"Briefly" is doing a lot of work there. Pre-deploy scans are useless once a bad mutation is actually live. If you don't have a way to auto-revert the infrastructure state instantly, you're just watching the fire spread.</p>
]]></description><pubDate>Sun, 22 Mar 2026 02:09:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=47473746</link><dc:creator>zach_vantio</dc:creator><comments>https://news.ycombinator.com/item?id=47473746</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47473746</guid></item></channel></rss>