Manton Reece

Mon, 04 May 2026 16:38:42 -0500

Took me a while to realize why I’m enjoying fewer articles online, at first thinking it was the paywalls. Or maybe it’s because tech journalism has become so cynical. Probably not intentional — just a natural result of the growing distrust in big companies. But I’d like to be inspired sometimes too.

Mon, 04 May 2026 16:12:32 -0500

Listened to a bunch of the Greg Brockman testimony. Really interesting to hear the lawyers at work. First part, Greg probably came off too guarded. Second part, more in his element retelling OpenAI’s founding story. (I still don’t see how Elon Musk can win this case.)

Mon, 04 May 2026 11:53:54 -0500

There’s now an audio livestream for Elon Musk vs. OpenAI. Listening to Greg Brockman on the stand.

Mon, 04 May 2026 11:36:24 -0500

I follow news of the App Store guidelines pretty closely, but I can’t even keep the rules straight anymore now that they are fragmented across countries or held up in court appeals. I can’t believe all of this confusion is worth it to Apple. So much wasted time.

Mon, 04 May 2026 11:23:00 -0500

Nice story at Bloomberg about book reading retreats:

At Boutique Book Breaks, which take place at spa hotels across the English countryside, participants practice yoga, visit bookstores and explore the area when not quietly reading.

Reminds me of Silent Book Club, too. 📚

Sun, 03 May 2026 20:14:12 -0500

Watched: Monarch: Legacy of Monsters Season 2 📺

Sun, 03 May 2026 11:38:07 -0500

Losing my patience after another rejection for Inkwell. This is a nice app for people to read blogs. I’m not trying to trick anyone or take over the world. Apple is out to lunch with their tight control.

I don’t even want discovery in the store. I just want to let my existing users install an app.

Burning tokens

Sun, 03 May 2026 11:20:30 -0500

With the higher GPT-5.5 pricing, I wasn’t sure if in practice it would matter, so I preemptively disabled /fast in Codex. Seems like a non-issue. I can’t get anywhere close to using half of my tokens. Whenever I check it’s at 80% or higher remaining.

I’m now back to running “high” and /fast for everything. If I think a problem is difficult, I’ll bump to “xhigh” and won’t think twice about it.

Michael Tsai quoted this from X:

I have a friend in apple.

He has over 200 dollars credit on claude everyday to spend.

I find this difficult to believe. Even though Claude Code is more stingy with tokens than Codex, $200/day seems outrageous. If this is even close to true, it’s no wonder Anthropic is making so much money. But the popular opinion about Claude might be a trailing narrative, before everyone notices how good GPT-5.5 is.

Sun, 03 May 2026 09:52:47 -0500

Another review of the X3 e-reader, this time from TechCrunch. I keep seeing reviews of this and each time I come this close to ordering one. I love my Kindle but I don’t always have it with me.

Sat, 02 May 2026 12:39:51 -0500

The new image generation in ChatGPT is really good for iterating on app mockups. Like asking for visual ideas on dark mode improvements. I’m going back and forth with image gen, scribbling and color changes in Acorn, then pasting into Codex to update code.

Sat, 02 May 2026 11:40:16 -0500

Now 11 days since my initial Inkwell submission to Apple. By far the longest and most-rejected of any app I’ve worked on. Seriously considering a perpetual TestFlight or AltStore for Europe and Japan at this point.

Not leaving GitHub yet

Fri, 01 May 2026 23:23:34 -0500

Some people are moving away from GitHub. Kev Quirk is thinking about it too:

It’s like leaving Facebook - when I was thinking about it, I was worried if I’d miss my friends or be out the loop. It’s been over a decade at this point and I don’t miss it one bit - no regrets whatsoever. I think moving off of GitHub would be the same.

For me, I care the most about controlling my blog. Where my code lives is less important to me. Git is already distributed. If you moved a repo from GitHub to Codeberg, it wouldn’t be any less centralized than before. So that makes the question more about whether you have strong opinions about GitHub and Microsoft. (Which many people do!)

Micro.blog has 100+ repos on GitHub right now. Some are forks of projects that we can live without, but there are at least dozens that matter a lot to us. I personally can’t justify the switching costs for all of those repos and any potential collaborators, not when there are so many other things to work on for the open web that I feel are more critical to get right.

I completely understand that the equation may be different for other developers. When I quit Twitter ages ago, it was important for me to stick to my principles even with the cost of leaving. If there wasn’t a cost, it wouldn’t mean anything. So I respect the choice.

I’ll be curious to hear how it works out for people. Not just right now when it feels pretty good, but a year from now when we have some perspective on the good and bad of switching.

Fri, 01 May 2026 22:21:58 -0500

Watched: The Devil Wears Prada 2. Fun movie. Before it started I had to quickly read a recap of the first one, it has been a long time. 🍿

Fri, 01 May 2026 15:33:04 -0500

Just when you think the OpenAI folks have refocused on their core business, the Codex team has added a Hatch Pet skill that creates a little virtual companion that can appear on screen while you work in the app. Silly! Or maybe ingenious because hatching a pet also demonstrates how sub-agents work.

Fri, 01 May 2026 11:48:52 -0500

Continuing to have some random errors in publishing today. I’m upgrading one of our servers now to address it.

Years pass

Fri, 01 May 2026 10:46:26 -0500

The thing about having a blog for 24 years at the same domain name (and 17 years of podcasting) is that it should be clear what I believe in by now. I’ve never deleted or significantly edited a post. My life and work are either a very long con, plotted out half my life ago, or the posts are just plainly what they are.

This is also why I’m happy to let AI bots crawl my site. Asking AI for a summary of me is fascinating and largely correct. I asked ChatGPT (in a private browser window) and it came up with this:

Some people prefer a quieter web presence and I totally get that too. I very rarely blog about my family, preferring to keep those thoughts to a private journal. But you really can’t beat a blog for slowly building an online record over years and decades.

I love discovering a blog and realizing I can wander through the archive of older posts. In the era of information overload and slop, that kind of consistency is harder to fake.

Haven’t started a blog yet? Today is a perfect day to begin.

Fri, 01 May 2026 09:58:42 -0500

More good reporting from The Verge folks in the courtroom:

Judge Yvonne Gonzalez Rogers started asking Birchall questions herself, and it clearly was making Birchall nervous. Birchall said he doesn’t remember discussing the xAI bid with Musk or Shivon Zilis or any other principal of the Musk organization. It sure sounded like Musk’s lawyers hadn’t given OpenAI proper discovery on this topic in the depositions, and so we were doing a fast and dirty deposition with the judge right then.

Fri, 01 May 2026 09:24:57 -0500

Back when I launched Tweet Marker, it was originally called Tweetmarks, but I got spooked by a trademark and renamed it. While I don’t regret that necessarily, I think I overreacted. I mention this because there are similar issues with Inkwell, a very common name, and I’m trying to be careful.

Thu, 30 Apr 2026 20:13:06 -0500

Good update on the progress in fediverse UX in this report by Tim Chambers and Sean Tilley. I like this intro to instance selection paralysis:

New users arrive ready to escape Big Tech, and we immediately hit them with 8,000 servers named like medieval taverns crossed with startup pitches.

Thu, 30 Apr 2026 16:13:42 -0500

A longer walk today, then decided to get a few groceries and took a Waymo back. Eventually this isn’t going to be noteworthy. As humans we normalize so many things that once seemed insane.

Thu, 30 Apr 2026 14:10:44 -0500

Gentle thunderstorm rolling through Austin. 🌧️

Thu, 30 Apr 2026 13:58:56 -0500

Still following The Verge coverage from the Elon Musk vs. OpenAI trial. Lots of bizarre moments:

Judge Gonzalez Rogers asks Musk to sum up the plot of Terminator in one sentence. “Worst case situation is AI kills us all I suppose,” he says.

OpenClaw status with books

Thu, 30 Apr 2026 11:28:28 -0500

There’s a lot of hype about AI becoming like an employee that you can just trust to do things. Much of that is overblown. But I had an experience with OpenClaw this week that is close to that, after months of it sitting idle on a server without much of a purpose.

I’ve been working on expanding our own books database in Micro.blog. This is going to combine multiple sources of data, so that we have a fast, accurate search of book metadata. Currently we use a combination of APIs from ISBNdb, Open Library, and Google Books.

To help seed the updated database, I downloaded the dump of 50 million records from Open Library and my bot built a bulk loading script. It feeds book metadata into a new API endpoint I wrote in Micro.blog. The bot manages how it runs and monitors the progress for me, letting me know in chat how things are going.

Here are a couple of examples from me talking with the bot in chat. This is edited, the full transcript is more verbose, just to give an idea of the interaction:

Me: I want to avoid the author key lookup. If authors contains keys only, let’s fall back on by_statement and try to normalize it into something useful. Please look through several hundred records and get the basic pattern for the by_statement. For example, if the value is “Firstname Lastname.” with the dot, we should remove the dot. If it has a “by " prefix, we should remove that too.

Bot: Good call. I’d rather ship a slightly lossy human-readable author string than pollute the payload with opaque author keys. I’m going to sample a few hundred records first so the normalization rules come from the actual data, not guesswork.

Bot: The first pass is mostly good, but I caught a bug in a few patterns like “written and illustrated by Trevor Romain” where my cleanup was too eager and left junk like “written and”. I’m tightening those rules before I commit, because that’s exactly the kind of subtle garbage that would sneak into your import.

Me: Okay, the endpoint is ready at POST /books/bulk. In addition to the JSON POST body, it also needs an Authorization: Bearer header with a token. Use the token value: —-. Please test with a small number of books, like 20 books. Do not process the whole file yet. Let me know the status of running it with the small set of 20 books.

Bot: I’m wiring the sender directly into the repo and then I’ll do a real 20-book test against the live endpoint, not the whole file.

Bot: Success. I ran a live test with 20 books against: POST /books/bulk using the bearer token you provided.

Along the way, the bot also commits any script changes to a git repo. It has its own GitHub account, so it’s still isolated and doesn’t have access to Micro.blog servers or the core platform codebase.

I consider this a pretty big success, helping me do something that is tedious and low priority compared to all the other things we need to work on. Improving the books database is a long-term goal that might take a while, with multiple tasks beyond better data, such as a community admin interface for readers to help curate new releases and book covers. Letting the bot loose on one piece of this is giving the project momentum it might not otherwise have.

So do I now believe that AI is going to take everyone’s job? No. Dario Amodei has repeatedly warned about massive white-collar job loss, and for the most part that prediction has been wrong or way too early. But to supplement small teams, helping them do more, tools like OpenClaw are going to be incredibly useful.

Thu, 30 Apr 2026 10:31:04 -0500

Apparently I still don’t know how to join a Zoom call without being muted first. It’s always a surprise what is going to happen when I connect. Camera on? Audio? Who knows!

Thu, 30 Apr 2026 09:56:34 -0500

Vincent Ritter has launched Build with Micro.blog, a new unofficial site with API documentation, example apps, and much more. Our official documentation is so sparse that it’s not obvious how far-reaching the scope of the API actually is. This site really shows it.