Here are some slop “signs” that I find triggering:

• Quietly
• Load-bearing
• Not one. Not two. Just three phrases destroying the flow of all online writing.

They’re all over the internet now! You see this most when there’s pressure for volume. Instagram and LinkedIn posts, high-volume, low-quality sites like The Verge. Outside of the headlines, I think people barely read these things anyway. But it has also violently infected programming blogs - largely because I think we’ve gotten so comfortable using LLMs for so many other parts of our work.

I recently had a few different scans of my body and brain done. Hooray for turning 40! At each imaging center I was given a USB drive “with my images on them.” It turns out those images are in a format called DICOM, and they usually come bundled with some kind of viewer application.

These things are a disaster!

• When you open them, you get to input a password made wholly of easily-findable data like date of birth and national ID number.
• The folder structure is a mess and differs from provider to provider. Just finding the DICOM is annoying even for my doctors.
• They ship old versions of free DICOM viewer software like MicroDicom and Weasis. These naturally fail OS integrity checks, which means you either get to bail, dig through OS settings, or call your grandson.
• The disks have known security insanity on them like autoexec.bat. In 2026!

This could be improved easily:

My AI coding setup has been evolving the last few months. Here are some things I’ve tried and moved on from:

• Gas Town. It’s just too much to wrap my head around right now.
• Pi and custom harnesses. I’m not at the stage where I need to deeply customize my workflow, starting from zero. I’m also not at the stage where I’m frequently switching models for different tasks. The Claude CLI is still good for me at this stage.

Here’s my current simple-to-use setup today:

Everyone is putting AI in their browsers now. Good (maybe even great!) browsers have been discontinued so users can focus on AI.

I’m not opposed to using AI agents for all sorts of things, but I don’t feel comfortable giving it nigh-unfettered access to the web. I’m not ready to let LLMs take on life-altering responsibilities like booking flights, looking at my banking sites, or reading my emails. I don’t trust their data retention policies with potentially sensitive context like calendars or emails. Nobody’s

All of the exciting AI coding is happening in terminals. Codex is good, the various VSCode forks are good, but if you’re doing multi-agent orchestration you’re generally using terminal UIs, roped together with Gastown, agent-deck, OpenClaw, lemonaid, or something else.

It’s gratifying, as someone who never left the terminal for a “grown up” IDE, to see how small programs piped together is the paradigm for innovation here. The stuff that makes it possible? Simple, largely open-source tech:

A few days ago my co-worker Bob turned me on to Beads. Beads is a step up from things like PLAN.md when managing work for coding agents, because it provides more structure, is easy for agents to parse, and provides things like progress tracking for multi-agent workflows.

I was intrigued by the setup because it seemed like a way to improve my agent’s ability to work autonomously, but I needed a way to try it out without stepping on top of some complex multi-person projects at work. I decided to use bd and a coding agent to implement a neovim plugin for managing beads.

The end of podcasting as a viable cottage industry really does seem to be here now, and the end of podcasting as a culture-moving media format has arrived. Amy Poehler won the first podcasting Golden Globe for a “hang out and promote my new project” podcast. Most celebrity podcasts are this way. Even the ones that ostensibly have a theme: Smartless is barely anything anymore. They’re warm applesauce, and they dominate the format to the point that ad revenue is draining away from a lot of better shows.

Pablo Torre is on episode 506 of TrueAnon¹, which is mostly about the NBA-adjacent poker fixing scandals, but touches on sports betting. The fact that data collection is not a neutral activity comes up repeatedly.

Player performance is monitored and measured for non-nefarious reasons: players and teams both benefit from better understanding of strengths and weaknesses in different ways. Pablo makes the case that the mere existence of this data - the predominance of statistical analysis in front offices and the advanced stats published by the leagues - changed the culture of American sports in negative ways. Rationalization of athletic performance led fans to believe the could get some edge (alpha in the financier’s language), and sports gambling was the natural outlet for this.

I’ve had a record player for at least 20 years. For the last 10 or so it was an Audio Technica LP120, which is on the upper end of ’non-audiophile’ turntables. Swappable cartridges, tons of tracking force adjustments, speed adjustments and strobes to check for accuracy. Direct drive. I ended upgrading the cartridge at some point. I loved that turntable, and it was darn reliable.

I did manage to fry it on 220v here in Singapore, despite the fact that it advertised compatibility with 220v. After it broke, it didn’t take me long to find a successor: an Audio Technica LP70X, which is in many ways the opposite: Fixed cartridge, no tracking force adjustment or speed adjustment. Belt driven.

I love diagram languages like mermaid.js and PlantUML because the text format that backs the diagram can be tweaked, takes up very little space in storage, and can be re-rendered at various resolutions any time you need. They’re great! I hate writing them. Mermaid has a different syntax for every diagram type, and they’re hard to remember. PlantUML is more consistent, though not totally, and in my experience can be quite verbose.