<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: brettdav</title><link>https://news.ycombinator.com/user?id=brettdav</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 24 Oct 2026 15:12:26 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=brettdav" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by brettdav in "Show HN: Ax-check.com – Can agents use your product?"]]></title><description><![CDATA[
<p>Interesting, thank you. I'll check whether a setting on CF might be interfering. The site checks headers for routing and response types, but it shouldn't affect access.</p>
]]></description><pubDate>Fri, 18 Sep 2026 23:02:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=49761416</link><dc:creator>brettdav</dc:creator><comments>https://news.ycombinator.com/item?id=49761416</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49761416</guid></item><item><title><![CDATA[New comment by brettdav in "Show HN: Ax-check.com – Can agents use your product?"]]></title><description><![CDATA[
<p>Integrating live bots to demonstrate live visitor experiences is a nice touch. I got an unexpected blocker (`Default Python urllib User-Agent gets 403'd by anc.dev`) I am not able to reproduce yet. Can you expose the scripts that the agents generate?<p>I took a different route with <a href="https://anc.dev" rel="nofollow">https://anc.dev</a> (scored 100 on ax-check) and rely on a wider variety of compliance tests. Beyond websites, it also audits binaries (think CLI tooling) to help inclined developers ensure their tools are discoverable by and useful to agentic systems.</p>
]]></description><pubDate>Fri, 18 Sep 2026 21:53:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=49760769</link><dc:creator>brettdav</dc:creator><comments>https://news.ycombinator.com/item?id=49760769</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49760769</guid></item><item><title><![CDATA[New comment by brettdav in "Show HN: Ax-check.com – Can agents use your product?"]]></title><description><![CDATA[
<p>The mcp audit at <a href="https://anc.dev/" rel="nofollow">https://anc.dev/</a> covers all flavors of mcp, including the recently launched webmcp. Remediation prompts, accessible equally by agents and humans, can help close any gaps. Usually one-shot, unless your site is crazy complicated.</p>
]]></description><pubDate>Fri, 18 Sep 2026 21:29:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=49760501</link><dc:creator>brettdav</dc:creator><comments>https://news.ycombinator.com/item?id=49760501</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49760501</guid></item><item><title><![CDATA[New comment by brettdav in "Shutting down our public encrypted DNS"]]></title><description><![CDATA[
<p>What about Cloudflare’s public DNS? <a href="https://developers.cloudflare.com/1.1.1.1/setup/#1111-for-families" rel="nofollow">https://developers.cloudflare.com/1.1.1.1/setup/#1111-for-fa...</a><p><pre><code>  1.1.1.2
  1.0.0.2
  2606:4700:4700::1112
  2606:4700:4700::1002</code></pre></p>
]]></description><pubDate>Fri, 04 Sep 2026 20:03:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=49569548</link><dc:creator>brettdav</dc:creator><comments>https://news.ycombinator.com/item?id=49569548</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49569548</guid></item><item><title><![CDATA[New comment by brettdav in "My local model setup on an M4 Pro Mac Mini"]]></title><description><![CDATA[
<p>Yes, that makes sense. Some of my models currently run in ollama while others require their own inference servers. I’m curious about custom inference servers in bifrost and the ability to orchestrate keeping some models warm in memory while evicting and cycling other models. All of which span different providers in bifrost (I think). Obviously I can get the mechanics from an agent, more wondering about any experience with something similar.</p>
]]></description><pubDate>Fri, 04 Sep 2026 03:27:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=49560183</link><dc:creator>brettdav</dc:creator><comments>https://news.ycombinator.com/item?id=49560183</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49560183</guid></item><item><title><![CDATA[New comment by brettdav in "Ask HN: Who is using MCP in production?"]]></title><description><![CDATA[
<p>I’ve deployed mcp to prod on numerous internal apps where ai-integration has been first party requirement. Obviously, agents can use an existing api, however maximum capability requires it to be well designed and documented. As many of you may have experienced, that is not something that can be assumed and improvements may be “impossible” or at least out of current scope.<p>That’s where mcp (and recently webmcp) have their benefits. By design, the protocols provide predictable structure that allows agents to discover and use the tools you provide.<p>I’ve had success using mcp variously as an agent friendly wrapper to an existing api and as a greenfield product designed for agentic workflows. Agentic workflows can string together multiple api endpoints together into a single tool call and or use their own dedicated backends.<p>To share my learnings, I’ve released a free tool at <a href="https://anc.dev" rel="nofollow">https://anc.dev</a> . While It’s still very much a work in progress, I’d love dialog and constructive feedback.</p>
]]></description><pubDate>Fri, 04 Sep 2026 03:10:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=49560090</link><dc:creator>brettdav</dc:creator><comments>https://news.ycombinator.com/item?id=49560090</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49560090</guid></item><item><title><![CDATA[New comment by brettdav in "My local model setup on an M4 Pro Mac Mini"]]></title><description><![CDATA[
<p>Can you share a bit more about your bifrost and llama swap setup? I’m facing memory constraints and am looking for a managed model solution that will help with hot swapping loaded models and stay-warm concurrency. Ideally with prioritization.</p>
]]></description><pubDate>Wed, 02 Sep 2026 03:02:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=49531224</link><dc:creator>brettdav</dc:creator><comments>https://news.ycombinator.com/item?id=49531224</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49531224</guid></item><item><title><![CDATA[Hacker sends email blast to Internet Archive Zendesk support ticket submitters]]></title><description><![CDATA[
<p>I received the following email as a response to a long closed support email. I don’t see anything to indicate it isn’t from Internet Archive’s actual Zendesk instance.<p>========<p>The Internet Archive Team (Internet Archive)
Oct 20, 2024, 05:22 CDT<p>It's dispiriting to see that even after being made aware of the breach 2 weeks ago, IA has still not done the due diligence of rotating many of the API keys that were exposed in their gitlab secrets.<p>As demonstrated by this message, this includes a Zendesk token with perms to access 800K+ support tickets sent to info@archive.org since 2018.<p>Whether you were trying to ask a general question, or requesting the removal of your site from the Wayback Machine—your data is now in the hands of some random guy. If not me, it'd be someone else.<p>Here's hoping that they'll get their shit together now.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=41894870">https://news.ycombinator.com/item?id=41894870</a></p>
<p>Points: 10</p>
<p># Comments: 5</p>
]]></description><pubDate>Sun, 20 Oct 2024 12:21:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=41894870</link><dc:creator>brettdav</dc:creator><comments>https://news.ycombinator.com/item?id=41894870</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41894870</guid></item></channel></rss>