Christopher Meiklejohn

This essay expands on Rift, which I published in May, and follows what’s happened since.

A short work of fiction. 1 Ruth called during an episode of Seinfeld that was being generated as Alexandre watched.

At nearly four in the morning, I was looking at a door with a pipe running behind it.

Zabriskie is a social app I am building around music, films, books, art, and the people who care about them.

When I was growing up, my parents wrote programs on a Commodore Plus/4, and later a Commodore 64.

Zabriskie is a social app I’m building around music, films, books, art, and the people who care about them.

Zabriskie is a social app I am building around music, films, books, art, and the people who care about them.

This is Part 2 of The Machine in the Lab, a series about using an autonomous research program built from large language models (LLMs) to build SetScope, a live Goose song guesser.

On Thursday, August 13, Goose opened the West Coast run in San Diego with “Animal.”

This is Part 1 of The Machine in the Lab, a seven-part series about building SetScope, a live Goose song guesser, with an autonomous research program built from large language models (LLMs).

In this blog post, I discuss three days in July 2026 when a single agent session ran away from me, and what those three days revealed about the concurrency assumptions buried in our development tooling.

Toronto to Detroit to Norfolk.

“Thank god this app rocks and I can live through the chompers.”

At 10:00 PM EDT last night I signed up for the $100 plan for Codex, the OpenAI coding agent that was driving most of the night’s work, because about a dozen Zabriskie PRs were in flight and I wanted them merged before I went to bed.

Someone on the Phish Facebook group reposted a TikTok overdub.

I’m building Zabriskie, a social app for live music, mostly with a coding agent.

I started this series because I’d been reading multi-agent papers for weeks and wanted a map I wished I’d had on day one.

If you’ve read this far, you’ve noticed that every paper I’ve discussed has a number next to it. 85.9 percent on HumanEval. 12.5 percent on SWE-bench. 25 percent on TravelPlanner.

Every agent system has to answer the same question eventually: how does it know it did the right thing?

If wave 1 was about role-playing and the agentic coding turn was about interface quality, there’s a parallel thread running through the field asking a more fundamental question: what should multiple agents actually do with each other?

By 2025, two things had happened.

“this app is the bees.

Wave 1 is the cluster of papers from 2023 that people actually cite.

If you try to read multi-agent systems papers without the vocabulary, you will get nowhere.

I’ve been reading multi-agent systems papers for weeks trying to figure out where the field actually is, and the honest answer is that it moves fast enough that any single paper is a snapshot, not a map.

By the fourth model swap I noticed that the part of the system I wasn’t swapping was the part holding the project together.

I was halfway through another PR, regenerating the proof file for the fourth time after rebasing on main, when I realized I couldn’t name a single PR the permit gate had caught.

Tonight, Goose was playing a very special set two.

I’ve been building Zabriskie for a few months now, mostly with AI agents.

I’ve been using Cursor 3 more over the last week or so because it makes it easy to move between models, and Cursor’s Composer 2 has been producing good results for me.

It’s 7 PM on a Thursday.

I gave a guest lecture on AI in Michael Hilton’s Foundations of Software Engineering course (CMU 17-313) today.

I watched two Claude Code instances step on each other’s database migrations last month.

I’ve been building Zabriskie – a social music app for live shows – with Claude Code for about six weeks now.

“If I knew the way, I would take you home” — Grateful Dead, “Ripple” Claude has a persistent memory system.

“What a long strange trip it’s been” — Grateful Dead, “Truckin’” The Problem Nobody Talks About When I was doing my PhD in Europe — splitting time between Belgium, Portugal, and Paris — I got diagnosed with celiac disease.

“When life looks like Easy Street, there is danger at your door” — Grateful Dead, “Uncle John’s Band” (A note on picking this quote: I asked Claude to find me a Grateful Dead lyric that fit the theme.

“Sometimes a notion gets a-hold of you, carries you away” — Grateful Dead, “Althea” The Saturday On March 7th, I sat down at 11am and started building.

Three weeks ago I wrote about building a social app in a week with Claude Code.

“Don’t let a heavy one hold back the dawn in you” — Goose, “(dawn)” The Third Place There’s a concept in sociology called the “third place” — not home, not work, but the place where you go to find your people.

Peter Van Roy and I just published a retrospective at PPDP ‘25 — the same venue where the original Lasp paper appeared a decade ago — looking back at ten years of influence from Lasp, the coordination-free programming model Peter and I built together in 2…

I spent the better part of a week building a social app with Anthropic’s Claude Code.

Ever want to test your system against Redis returning wrong values, like instead of returning an error, it returns an empty string?

Your developers are writing functional tests for their microservice and, when RPCs fail, they throw exceptions.

Ever wanted to just throw all sort of values at your database and see what happens to your application?

About two months ago I started prototyping this feature for visualizing API coverage in a microservice application through automated instrumentation: see where you have functional testing coverage, how many functional tests, and where you’re applying fault

You can also use Filibuster’s dynamic analysis linter to find microservice smells.

You can also use Filibuster’s dynamic analysis linter to find microservice smells.

You can also use Filibuster’s dynamic analysis linter to find microservice smells.

Integrated directly into IntelliJ, Filibuster can show you the RPCs that your service is making and directly inject faults on any of those RPCs.