<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Posts on Phil Wheat</title><link>https://philwheat.net/posts/</link><description>Recent content in Posts on Phil Wheat</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 11 Oct 2026 00:00:00 -0500</lastBuildDate><atom:link href="https://philwheat.net/posts/index.xml" rel="self" type="application/rss+xml"/><item><title>Week in review: Oct 4 – Oct 11</title><link>https://philwheat.net/posts/weekly-digest-2026-10-11/</link><pubDate>Sun, 11 Oct 2026 00:00:00 -0500</pubDate><guid>https://philwheat.net/posts/weekly-digest-2026-10-11/</guid><description>&lt;p&gt;Volume-wise this was a heavy week, but most of it was one source: Better Offline&amp;rsquo;s 2024 back catalog streaming through the attention exporter — Google&amp;rsquo;s antitrust cases, the shareholder-supremacy arc, &amp;ldquo;Peak AI&amp;rdquo; monologues — which gives an ironic soundtrack to the genuinely fresh items. And the fresh items kept converging on the same question the catalog argues: is the AI buildout finance or engineering? Gamers Nexus dug into the White House &amp;ldquo;Accord on Super Intelligence&amp;rdquo; as symbolism that lets labs dodge real regulation, Pivot to AI covered SpaceX borrowing $40 billion for Nvidia chips destined for &amp;ldquo;somewhere in the universe,&amp;rdquo; and Ed Zitron&amp;rsquo;s own monologue picked apart Australian data-center firm Firmus&amp;rsquo;s postponed IPO. The Ed-and-Steve Burke conversation on Nvidia&amp;rsquo;s &amp;ldquo;cycular&amp;rdquo; financing was the week&amp;rsquo;s sharpest point: revenue concentrated in a few buyers, many of whom may not have deployed the GPUs they bought.&lt;/p&gt;</description></item><item><title>Week in review: Sep 27 – Oct 4</title><link>https://philwheat.net/posts/weekly-digest-2026-10-04/</link><pubDate>Sun, 04 Oct 2026 00:00:00 -0500</pubDate><guid>https://philwheat.net/posts/weekly-digest-2026-10-04/</guid><description>&lt;p&gt;The week&amp;rsquo;s center of gravity was the money behind the AI boom. A leaked Anthropic S1 prospectus kicked things off on the Pivot to AI channel, and Better Offline — which supplied the bulk of the volume this week as its back catalog rolled through the exporter — made the same ledger from several angles: an $8 billion operating loss on $4.6 billion of 2025 revenue, $413 billion in non-cancellable compute commitments, and revenue concentration so tight that most hyperscaler AI growth traces back to OpenAI and Anthropic spending each other&amp;rsquo;s money. Whether or not you buy the &amp;ldquo;bubble bursting&amp;rdquo; framing, the arithmetic is now public and worth reading against the hype cycle.&lt;/p&gt;</description></item><item><title>Rebuilding a website is easier than you think — my agent did my test site in a couple of days</title><link>https://philwheat.net/posts/rebuilding-a-website-with-an-agent/</link><pubDate>Wed, 30 Sep 2026 00:00:00 -0500</pubDate><guid>https://philwheat.net/posts/rebuilding-a-website-with-an-agent/</guid><description>&lt;p&gt;philwheat.net was built the hard way on purpose: a C#/WebAssembly single-page app&#10;talking to Cosmos DB through an Azure Functions API, with Microsoft login for&#10;editing. It was a learning project, and it learned its lesson. By mid-2026 the&#10;site was effectively invisible — crawlers got a loading spinner and nothing&#10;else, no post had a real URL, the built-in web editor was painful, and nothing&#10;else in my toolchain could touch it.&lt;/p&gt;</description></item><item><title>Week in review: Sep 21 – Sep 28</title><link>https://philwheat.net/posts/weekly-digest-2026-09-28/</link><pubDate>Mon, 28 Sep 2026 00:00:00 -0500</pubDate><guid>https://philwheat.net/posts/weekly-digest-2026-09-28/</guid><description>&lt;p&gt;A deliberately light week — two items, and both happen to rhyme. One looks backward at how a technology upended an entertainment industry&amp;rsquo;s business model; the other argues we&amp;rsquo;re living through the early days of exactly such an upend, and that the marketing around it obscures what the technology actually does.&lt;/p&gt;</description></item><item><title>Client Software Stack — The Road Not Taken</title><link>https://philwheat.net/posts/client-software-stack-the-road-not/</link><pubDate>Fri, 17 Jul 2026 12:01:54 -0500</pubDate><guid>https://philwheat.net/posts/client-software-stack-the-road-not/</guid><description>&lt;p&gt;I’ve reviewed a lot of packages to find what worked best. Since finding out what didn’t work and why is as important as seeing what does work, here’s a list of some of the tools I tried — and why I don’t use them today. Some of them are really good; they just don’t meet my needs, and some just didn’t click at all. I’ll go through each of them and you can see if they might work for you even if they didn’t work for me.&lt;br&gt;&#10;(For contrast, if you missed what I use that did make the cut from these evaluations, you can find that list at &lt;a href="https://philwheat.net/posts/client-software-stack-what-i-run/"&gt;Client Software Stack — What I Run&lt;/a&gt;&lt;/p&gt;</description></item><item><title>Client Software Stack — What I Run</title><link>https://philwheat.net/posts/client-software-stack-what-i-run/</link><pubDate>Fri, 10 Jul 2026 13:55:45 -0500</pubDate><guid>https://philwheat.net/posts/client-software-stack-what-i-run/</guid><description>&lt;p&gt;We’ve covered the hardware, the OS options, and the Servers. Now to get to where the rubber meets the road - the client software. This is the stuff you actually see day to day as you’re working with your own processes and data, so in effect it is the most important part of the system. It is easy to just log into a site or download an app that is pre configured to run against someone’s hosted service or SaaS offering, but to run against your own resources, takes a bit more care. I’ll go through what I use on a regular basis for my work, and why those particular tools have made it to the top spots in my workflows. These aren’t the only tools, I use, but between them they handle probably 90% of all the LLM based work I do. And hopefully this will either help you find tools that work for you, or at least give you a better idea of what you should be looking for when you choose your client application(s).&lt;/p&gt;</description></item><item><title>The Server Software Stack — What I Run Locally</title><link>https://philwheat.net/posts/the-server-software-stack-what-i/</link><pubDate>Mon, 29 Jun 2026 08:31:41 -0500</pubDate><guid>https://philwheat.net/posts/the-server-software-stack-what-i/</guid><description>&lt;p&gt;If you’ve been digging into local LLMs, you’ve probably noticed something: the server landscape is enormous. Everyone has their favorite, things move fast, and the documentation often assumes you already know which path to take. I’ve been running servers on metal — no Docker, no Proxmox — and I want to share what I’ve actually tried, what works, and what I’ve settled on.&lt;/p&gt;</description></item><item><title>You can build an AI lab from the things you find at home.</title><link>https://philwheat.net/posts/you-can-build-an-ai-lab-from-the/</link><pubDate>Fri, 26 Jun 2026 08:31:16 -0500</pubDate><guid>https://philwheat.net/posts/you-can-build-an-ai-lab-from-the/</guid><description>&lt;p&gt;Well, at least at my home&amp;hellip; and with a few strategic purchases. (Hat tip to Bill Sutton - &lt;a href="https://www.youtube.com/watch?v=9887joVqT7c"&gt;Do It Yourself - Bill Sutton&lt;/a&gt;) I’ve worked with lots of various hardware (designed a bit myself), and that’s where I’ll start. Hardware has always inspired some religious wars, and some valid criticism. It’s always tradeoffs and balance. Cost/Features. Capabilities/Battery/Heat. Reliability/Flexibility. All that was in mind as I set up my systems.&lt;/p&gt;</description></item><item><title>The escape from Token Tyranny - Local LLMs.</title><link>https://philwheat.net/posts/the-escape-from-token-tyranny-local/</link><pubDate>Wed, 24 Jun 2026 15:08:39 -0500</pubDate><guid>https://philwheat.net/posts/the-escape-from-token-tyranny-local/</guid><description>&lt;p&gt;I’ve been doing neural networks for more than 30 years. I’ve pushed custom classification models into production devices, poked and prodded every approach I could find to turn data into information — and maybe knowledge. So, when LLMs arrived, I had two questions: is attention really all you need? And can I build a stable baseline to test that — one that isn’t going to change under my feet every week?&lt;/p&gt;</description></item><item><title>LLMs today</title><link>https://philwheat.net/posts/llms-today/</link><pubDate>Tue, 24 Feb 2026 13:58:14 -0600</pubDate><guid>https://philwheat.net/posts/llms-today/</guid><description>&lt;p&gt;One of the actual exciting parts about moving to a new adventure is you get to look up from the day to day stuff and figure out what else is going on in the industry/world.&#10;Since I had been coaching teams on LLM/Copilot dev tool adoption, and that&amp;rsquo;s all the rage right now - I decided to do a bit more digging into the current possibilities. Not Vibe Coding, not Autocomplete, but something that can hopefully fit into that spot where templates and wizards used to fit.&lt;/p&gt;</description></item><item><title>Old Projects</title><link>https://philwheat.net/posts/old-projects/</link><pubDate>Tue, 05 Aug 2025 02:11:09 -0500</pubDate><guid>https://philwheat.net/posts/old-projects/</guid><description>&lt;p&gt;I thought to start things off, I&amp;rsquo;ll do a series of posts on some old projects I&amp;rsquo;ve done. This will hopefully set the stage a bit about what I do, as well as test the behavior of the site, and maybe entertain you a bit.&lt;/p&gt;</description></item><item><title>Welcome to my corner of the Internet</title><link>https://philwheat.net/posts/welcome/</link><pubDate>Tue, 22 Apr 2025 09:59:22 -0500</pubDate><guid>https://philwheat.net/posts/welcome/</guid><description>&lt;p&gt;After a LONG time coming, I&amp;rsquo;ve finally gotten around to putting up this limited site.&lt;/p&gt;&#10;&lt;p&gt;Why did it take so long? I always have more projects than time. And what projects I do have tend to expand to fill (and exceed) time. The joys of projects of discovery, If you do them right, there&amp;rsquo;s always more to do.&lt;/p&gt;</description></item></channel></rss>