On the Web on joe blubaugh

We lost the ability to write online

Tue, 04 Aug 2026 20:40:39 +0000

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.

And it happened so quickly; I think it took less than a year. For some people, surely less time than that. Don’t get me started on the comments! The sad thing is that it has made so many websites unreadable. The sites that used to sustain some online technical learning are painful for me now. Most of the information I find there doesn’t ever show up in books, and the other sources here are insufferable programmers on YouTube. I really don’t know what to do here other than suffer.

DICOM is a disaster for patients

Tue, 04 Aug 2026 13:35:07 +0000

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:

in addition to the DICOM files, generate a JPG per slice. This is all that most patients will need for their own use, and they can then actually use them on phones and the like.
everything should be in a single application bundle like a game installer would be. Offer an option to “export my images” to either DICOM or JPG formats when patients need to share images with non-clinicians.

My AI coding setup today

Thu, 16 Apr 2026 04:38:34 +0000

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:

Claude Code CLI. I use a variety of plugins with Claude Code. I don’t use IDE integrations or the Claude desktop app.
- superpowers provides a basic software development framework that really improves the quality of initial implementation. I don’t even think about this one, it gets invoked automatically all the time.
- autoresearch provides a simple optimization loop for measurable tasks. I recently used it to cut down bundle sizes in one of the programs my team ships.
- Slack’s official plugin for reading messages.
- gdocs-cli. Anything at work that doesn’t happen in Slack happens in Google Drive.
- Grafana-internal skills and tools for our wiki and queries.
- bugbot-loop listens for PR comments and responds to them by implementing good suggestions and resolving bad ones, over and over.
Cursor BugBot installed in our Github repositories. This is the tool that I think provides the right combination of ease and high quality in its review processes. Combining this with bugbot-loop immediately increases PR quality without intervention on the part of any humans.
agent-deck. A Tmux layer that provides management of multiple agent sessions. It understands git, especially worktrees, and watches the state of sessions. This way I can tell which of my sessions is still churning, and which are idly waiting for intput.
ars contexta. This one is a little complicated to explain, but it’s a knowledge base that an agent automatically maintains and refines over time.

So, my work setup tends to look like this: I have a custom skill for summarizing Slack that runs once a day via launchctl. It DMs me a summary each morning that helps me build up my to-do list. Throughout the day I throw my notes into ars contexta. I used to use Logseq for this, but I’m doing less manual creation of notes now.

I have an organized set of sessions in agent-deck.

A section of coding tasks - each associated with a set of PRs. When the PRs are finished to main they’re killed and cleaned up. After the initial coding, when the PR is updated I start /bugbot-loop for up to 10 iterations.
A set of longer-lived “research” sessions where I’m keeping notes about and getting feedback on larger ideas and direction for projects. These usually end up writing markdown files that are consumed by ars contexta or written into things like Architecture Decision Records for a given project.
a single ars contexta session where I throw in notes. I can also ask this to search recent Slack activity or gdocs for information to add to notes.

As far as concepts and tools I’m interested in investigating to continue improving my workflow:

agent-deck “conductors” to increase autonomy for task-oriented sessions even more.
Archon. Providing a little more determinism in my software workflows could be nice. Compare “fix a bug” to “explore the codebase for improvements”. These practices should probably look different, and . Seems like a promising way to increase autonomy with some of these tasks.
Spec-driven development. I need to dedicate more time to reading and prototyping here. I’m optimistic about improving autonomy in my sessions via more detailed planning.
Context graphs. The concept feels like it may be able to encode a lot of “Chesterton’s Fence” information that agents struggle with. In particular I’m interested in it from an Observability standpoint. Every running software system is unique, and we’ve never been able to establish industry-wide practices that everyone follows to the letter. Semantic Conventions and the like are moving Observability in that direction, but discovering structure is somewhere that LLMs are very promising for.

Zen: A Browser You Can Love

Sat, 07 Feb 2026 01:17:18 +0000

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

So I don’t want it in my web browser, which is where most of this work gets done in 2026. I’ve been using Firefox at home and Arc at work, and they’ve got different problems. Arc is over. “The Browser Company” has gone all in on an AI Browser that’s not dissimilar to OpenAI’s browser. Firefox added AI features in November and is only now adding controls that can give you some control over data sharing.

Fortunately, someone recommended Zen to me. Arc’s approach to tabs always clicked with me: every view of a profile, even in a different window, has the same tab set. You can use multiple profiles (“spaces”) to manage different tab groups, and different sign-in contexts. Zen’s latest release uses the same behavior, and it’s delightful. It has a simple but very useful split-view feature. I use it for things like reading the meeting notes and having the video call in the same window, or comparing two related documents without having to tab back and forth. Where it has any AI features at all, they are limited and require advanced settings to turn on. You’re not going to get them intruding on you, at least for now.

It turns out I’m not the only one who’s had this experience.

Multi-agent coding and the resurgence of the terminal

Thu, 05 Feb 2026 15:23:52 +0000

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:

tmux: lemonaid, agent-deck, and Gastown all use tmux panes and windows to let you jump to the right place and give the right info to the right agent at the right time.
git: Lots of work-tracking and communication systems (like beads) use git. Git worktrees are an essential component for multiple agents to work on the same codebase at the same time.
sqlite: agent-deck uses this for communication, and so many other tools seem to as well.