I’m really excited to introduce a project I worked on with various AI agents the other night, which I think represents a new way we might build things in the future.

First, the problem: My WordPress site has 5,600+ posts going back decades, and I had some categories that were old and I didn’t really use anymore, and I wasn’t happy with the structure. Every time I made a new post, it irked me a little, and I had this long-standing itch to go back and clean up all my categories, but I knew it was going to be a slog.

Let me present Taxonomist, a new open-source tool you can run with one copy-and-paste command line that solves this problem. Here’s the idea:

1. You run this code in your terminal, and it spins up a Claude Code instance that asks you for your URL.
2. Then it takes that and figures out what type of site you have, which APIs are available, and starts downloading all your posts locally for analysis.
3. Sub-agents analyze every post against your current categories and thinks about suggesting new ones.
4. It previews all the changes.
5. Tries a variety of ways to authenticate against your site and make all the changes.
6. Logs everything locally, so anything is reversible later.

THIS IS VERY ALPHA. PROBABLY BUGGY. BE CAREFUL WITH IT. PATCHES WELCOME. MAYBE MAKE A BACKUP OF YOUR SITE BEFORE YOU CHANGE IT.

It kind of just worked. I ran it live against ma.tt and it cleaned up a ton of stuff pretty much exactly how I wanted. But there’s a lot of weird stuff happening here, so I don’t know quite what this is yet.

1. It’s very non-deterministic! There is some pre-written code, and probably could be more, but a lot of the code is generated on the fly by your agent. This creates interesting bugs where people testing with less powerful models had some odd behavior.
2. I kind of want a directory of these useful AI agents on WordPress.org, but also, there’s something a little strange about trusting a remote shell script to run on your machine.
3. I tested this with Claude, but there’s no reason Codex couldn’t use the repo in the exact same way, and I’d love to improve the quick start script to start by detecting all the agents you have, asking which you’d like to use, and also which directory you’d like to work in. I think we could kill the cd taxonomist-main && claude "start" part of it.
4. Because much of the code and commands are generated on the fly from prompts, it’s very resilient! I’ve seen people try it, and it ran into errors with libraries or whatever, but it just figured out how to work around them.
5. I’d love it if, at the end of every session, there was a moment for self-reflection where the agent would take the repository and suggest upstream issues and PRs based on anything that went wrong. Then this could recursively self-improve very quickly.
6. There are some obvious improvements to this, for example, doing this for tags. Sometimes it creates too many categories when you might only want 3-5 for your theme.
7. One fun thing is a bunch of the work of this just uses public WordPress APIs, so you can run it against any site! I like using distributed.blog as a demo. It’ll still do all the fun downloading and analysis and everything, you just won’t be able to make changes.
8. I now have a local cache of all my WordPress posts I can do other interesting things with, and that’s cool.
9. The logging and reverting probably still has some bugs in it.
10. You can riff with it along the way, so for example, it suggested I get rid of my Audrey category because it didn’t have enough posts, and I asked it to look at all the companies on Audrey.co website and categorize any posts that talk about them as Audrey, which created like 50 more.
11. I want to check the GitHub repo for any updates before it starts, and maybe periodically, because it’s iterating and improving really fast.
12. It’s not the default but the entire thing is way more pleasant if you run it with skip-permissions. So testing I usually run the one-liner, exit, resume with skip.
13. You can see some of my prompt history in the Github but I apologize it’s not comprehensive, I also used Gemini and Codex with this and got lots of value from them.

So, not sure what this is, but please check it out, play with it, submit improvements or ideas, and think about what’s next. Might host a Zoom or something to brainstorm.

The final thing I say is that this was a very different process of writing software for me. Instead of staying at the computer the entire time, I found myself going away for a bit, napping and dreaming about the code, coming back with new ideas and riffing on them. Maybe I’ll return to my Uberman polyphasic sleep days? Nap-driven development?

BTW I have lots of thoughts and feedback for Emdash but I thought this was more interesting, will try to get that out later tonight. One preview: TinyMCE is a regression; they should use Gutenberg! We designed it for other CMSes and would be fun to have some common ground to jam on.

Might do the same for you

In The Relentless Missionary Creating AGI: Demis Hassabis, the latest episode of the Founders podcast, David Senra compresses by Sebastian Mallaby's book, The Infinity Machine: Demis Hassabis, DeepMind, and the Quest for Superintelligence, into 55 minutes of pure inspiration. Not just because Demis is a hugely inspired and driven dude, but because a pile of ideas came to me while I was listening.

Big fact

YouTube has 2.7 billion monthly users.

Here's almost looking at you

Imagine scattered bits of coffee grounds, floating in space in front of your face, a few inches to a few feet away. Among them, blurred filaments float around, like zero-gravity worms. These are bits of debris inside my left eyeball, not far from my retina, exfoliated, I am told, by my cornea, which is slowly healing from the effects of cataract surgery that required a somewhat aggressive emulsification of the lens before a new replacement lens was installed.

An interesting thing: if I don't move my eyes, the debris slowly vanishes, erased by my brain as if by Photoshop's healing brush. Then they reappear when I move my eyes. Strange shit.

Observations

Explore these observatories. Read what they are about and how they are produced. One more way (within which are many more ways) that the world will never be the same. Bonus link in the same vein. Big HT to Jim Cowie of the Berkman Klein Center, the Internet History Initiative, and much else.

Unanswered

I still have questions about two Dorothy Parker quotes.

“A newspaper is not only a collective propagandist and a collective agitator, it is also a collective organiser.” — Vladimir Lenin

In 1902, Lenin argued that his revolution needed a newspaper of its own, and that newspaper was (unironically) named Pravda, which means truth in Russian.

“The standard communications playbook just doesn’t apply to us. We’re not a typical company. We’re driving a really big technological shift.” — Fidji Simo, 2026

Simo, OpenAI’s CEO of Applications, explained this to OpenAI staff as to why OpenAI had just bought TBPN. Different century. Same logic to explain an emerging new socioeconomic order, a new post-revolution reality.

To recap, OpenAI, weeks if not months before its public offering, has acquired the Technology Business Programming Network (TBPN). It is a daily, three-hour live tech talk show hosted by founders Jordi Hays and John Coogan. The show had 58,000 YouTube subscribers, $5 million in revenue last year, and a cult following in Silicon Valley. It was profitable, had no outside investors, and was growing fast. As a former media person, any media exit is a good exit. Congratulations to the founders.

Now let’s dig into what OpenAI really bought and why.

Think of TBPN as a room. A room where people in tech come and talk openly, without having to worry about the antagonistic queries that big media is often posing them. They go because it feels like peers talking, not press interrogating.

If you lived through Internet 1.0, CNBC’s morning show had the same vibe. ESPN’s SportsCenter did the same for the cable sports revolution. They don’t speak to power. They amplify power. TBPN made that playbook its own.

The best part of the announcement is where TBPN sits inside the OpenAI org and who it reports to. The show sits under “strategy” (and not communications) and will report to Chris Lehane. He is OpenAI’s chief political operative, the man associated with coining “vast right-wing conspiracy” as a deflection tactic during the Clinton White House years, who built Fairshake, the crypto super PAC that spent hundreds of millions targeting anti-crypto candidates in 2024.

You don’t put an editorially independent media property under your political operative. That’s not a media strategy. That is part of overall strategy. But they still have to sell it as keeping it editorially independent. Pravda was technically editorially independent too.

Anyway, maybe I have lost my rose-tinted glasses, but when a company says “do no evil,” you know what they are going to do. And if a press release mentions editorial independence four times, you know where that is going. And if you have to invent a new phrase, “Editorial Independence Covenant,” then I don’t really need to spell it out for you.

“The conscious and intelligent manipulation of the organized habits and opinions of the masses is an important element in democratic society.” — Edward Bernays, Propaganda, 1928

Bernays, who was Sigmund Freud’s nephew, invented the PR industry. He thought of it as a key part of corporate design. He was hired by corporations such as United Fruit and American Tobacco to do exactly what OpenAI is doing now. Build the perception layer around a product by presenting it as a massive societal shift.

The Soviet term was agitprop. The Silicon Valley term is earned media strategy. A century apart, history still rhymes.

Related Reading

• OpenAI: The Fix Is In — How OpenAI is engineering its IPO narrative through circular financing and retail ETFs.
• OpenAI Has New Focus (on the IPO) — On Simo, Facebook-style engagement loops, and the real game being played.
• More Magic Math from OpenAI — The PE deals, the JV structure, and why the real product is the IPO prospectus.
• The New Announcement Economy — How OpenAI mastered the press release as a capital-raising instrument.