jdilla.xyz

🪦 Project Graveyard: Papagei Terminal 🦜

2025-11-06

I’m trying to get better at building in public and at celebrating projects that end up as dead ends. Take this in that spirit.

What it was

Papagei Terminal allowed a user to spin up virtual machines like they were slack channels to make it easier to use >1 Claude Code instance at the same time and make it easier to use Claude in --dangerously-skip-permissions mode.

Here is an early prototype. Future versions were way better!

What went well

I think I had a really clear idea of who this was for and the need that it was serving.

This is by far the most ambitious technical project I’ve built. I was able to use it to make meaningful code changes across several projects. I learned a bunch about working with AWS and with agents.

I actually got to the point where a tool I built was able to make code changes to other projects. That was really motivating.

Why it didn’t work / why I’m shutting it down

At the beginning of the summer, there really wasn’t a product that allowed you to use more than one Claude Code at the same time without putting real effort into understanding Git Worktrees. Conductor was experimenting here, but it was all local.

Between May when I started working on this seriously and when I got it to the point where I was really starting to enjoy using it, everyone launched a version of this and I was no longer convinced that I had something unique to bring here.

What I learned / what I would do differently next time

Realistically I probably started building this too late. I also don’t think I am embedded enough in the community of software developers to get a following here.

I wasn’t active enough in recruiting early users.

Good tokens 2025-10-31

2025-10-31

A very happy šŸŽƒ Halloween šŸ¦‡ to you and yours.

Worth your time

The most American Building. My grandfather slept in it while it was unfinished in between training stops in World War 2. My father took classes in it. I went to it on field trips. It’s a wonderful building.

Preach, Nabeel, Preach. I wonder why ā€œeducationā€ rather than ā€œageā€ has been what has sorted our politics šŸ¤”.

On relationship between growth and trust, arguing that living through periods of higher GDP growth leads to higher societal trust. On one level, this squares well with the idea that trust is a mixture of competence, commitment, and character, with societies delivering growth being seen as competent. On the other hand, I would expect higher levels of trust to also unlock opportunities for faster growth.

Things I learned

Home field advantage in the NFL is actually real and it basically disappeared in 2020 when no fans were in the stadiums. Via CrƩmieux.

More than 98% of new vehicle sales in Norway were EVs in September. From Elective via Anton.

Unconfirmed but from a reliable source: Amazon drivers are paid 12 cents per packaged delivered.

A growing share of Americans (+13%) say Religion is gaining influence in American life according to Pew. I’m not sure how to square this with the thing I learned last week, that support for declaring the United States a Christian Nation is falling amongst Christians or that the fastest growing Catholic sects are the strictest ones. Strange things are happening!

For the first time in 35 years, no rap songs are in the top 40. Rolling Stone.

Musings

Should we care about process or outcomes? Some really successful people (see Tom Brady here ) seem more to favor the process over the result while others favor the result over the process (see Phil Knight / Nike and Sam Altman). How should I make sense of this?

What would have to change for Western Society to become less individualistic? Is it possible for Western Society to become more individualistic? What would it look like to short individualism?

LLM corner

Episode 3 of Dangerously Skip Permissions is next week: LLM pricing is broken, but not in the way that you think with my friend Anjali Shrivastava.

Supra Podcast: How AI is changing the future of software development

2025-10-28

I got to join Marc and Ben from the Supra podcast to talk about how AI is changing how software teams operate.

Three things I took away from this conversation.

First, is that there are some things that AI doesn’t change. At the end of the day, you’ve still got to define the problem, define the approach, define the details. AI changes the tools, the artifacts, and the process, but it doesn’t change the basic facts of problem solving.

Second is AI is changing how software is made at three levels simultaneously: individuals, teams, and organizations. Individuals are trying out tools (e.g., Claude Code) and putting them into their workflow. Then there are some teams that are starting to adopt some of these tools en masse and reorganize their processes around them. Finally, there are organizations that are trying to figure out what all of this means for the ā€œstandardā€ way of working and shipping software.

To get this right, organizations need to be willing to change across 4 dimensions:

  • Tools - What are the tools that are available to us? What are their benefits and limitations?

  • Tactics - How do we coordinate with these tools to achieve a result? What are the artifacts that are created? What is the size and roles of people on the team?

  • Training - How do we build competence on these new tools and tactics? How do we give people space, opportunity, and resources to experiment?

  • Values - What does great work look like? What is important and celebrated?

Without all of these working together, organizations will fail to get value out of a transformative technology — and I have to be honest, now is a moment where I’d rather be at a small company experimenting with new ways of working than at a large company where I have to be concerned about how this works at scale.

You can find the whole episode here:

  • Spotify: https://open.spotify.com/episode/7nozDSwSk3fuAK4TQWxm5l?si=oA0qIwIJShqTCjMOLFFC0Q

  • Apple: https://podcasts.apple.com/us/podcast/81-i-spent-3-months-at-an-ai-native-startup-where/id1737704130?i=1000733726676

  • YouTube: https://youtu.be/GbOw8_JViPA

  • Substack: https://suprainsider.substack.com/p/81-i-spent-3-months-at-an-ai-native

Book Thoughts: Becoming Trader Joe

2025-10-24

Similar to Shoe Dog — and different in the way that Nike is different from Trader Joe’s.

Three things I want to take away from this book:

  1. Joe was incredibly structured in how he thought about problems. He wanted to have a retail store where he paid people well which required him to have goods that had a high price per amount of space they took up. He was willing to cycle through lots of weird ideas (including things like gun ammo) as long as they met this criteria.
  2. Discontinuities. Trader Joe’s would specifically target little edges in product categories. As an example, they would become experts in the regulations for say cheese or butter to build limited edition products. In particular they did this on the product side, carefully understanding product categories, and on the regulatory side, carefully reading the fine print to find edges that others didn’t have. An example of a discontinuity is being willing to sell coffee in non standard container sizes or for a limited period of time.
  3. The concept of double entry retailing, which is another way of saying that decisions are interconnected. As an example, paying people more reduces shrinkage.

I didn’t know whether or not to laugh or cry when he said that Trader Joe’s target customer is overeducated and underpaid.

This book helped me better understand how retail, goods, and media are interconnected. The transition from network tv to cable tv happens at the same time as Trader Joe’s is shifting away from homogenized consumer packaged goods to the more varied assortment we see today. A similar version of this happened with Facebook and the DTC brands of the 2010s.

Good Tokens 2025-10-24

2025-10-23

Worth your time

The Alpha Terrace Historic District in Pittsburgh, PA. One of my dream places to live.

My guilty pleasure on YouTube right now are videos claiming Ancient Egyptians had access to advanced technology that allowed them to machine vases out of hard stone. I’m agnostic as to whether or not this is true, but I can’t look away! A second thing that makes these videos delightful is that they all pit themselves against mainstream archeology which just cracks me up. Who are these mainstream archeologists? What are they doing to hinder this message? I see the evidence for advanced manufacturing but these mainstream archeologists seem like a mythical species.

On seriousness.

Why is Switzerland so rich? This is good, but I think it misses a couple of things. First, Switzerland was spared the physical and human losses of both World Wars. Second, there’s a cultural element that the post doesn’t speak to. Switzerland is both highly individualistic and highly communal, a mix of live-and-let-live and we’re-all-in-this-together that I believe allows it to make more pragmatic decisions, the benefits of which compound over time.

Some of the strongest US-China copium I’ve ever seen.

Creating a village for your child. I wish it were easier to do this.

What happens when someone dies on an airplane. Via Uri.

Things I learned

11 states and half of the counties in the US have more senior citizens than children. This sounds outrageous but I’m curious how much this has changed over time and the degree to which this is just more about longer life spans. Someone should analyze this the way Brian Potter analyzed US pedestrian deaths.

Costco’s Kirkland Brand drives more revenue than all of Procter and Gamble combined.

One of the great joys of having children is that they ask obvious questions you haven’t considered. This week it was: ā€œWhy do we call it a piggy bank?ā€ 1 It turns out that this (possibly) comes from the name of the clay, pygg, that was used to make jars for storing coins and that shaping them like pigs was a visual pun.

Support for declaring the United States a Christian nation is falling amongst Christians.

Musings

Someone told me this week that in France they say that there are six reasons someone will pay for something: Security, Pride, Novelty, Comfort, Money, Friendliness.

LLM corner

The Tiny Teams Playbook. This rhymes with some of what I learned this summer while ā€œinterningā€ with Roo Code. See also prototype first development.

Dead Framework Theory - the idea that LLMs are freezing frameworks like React into the internet. I thought like this at first, but I no longer think that this is true and I actually think LLMs will make it easier to bootstrap new frameworks provided those frameworks have real advantages over what they’re replacing because LLMs make it so much easier to adopt new tools.

Peter Steinberger’s Agentic Coding Guide.

Living Dangerously with Claude.


  1. The actual question was much funnier. My 5 year old made a piggy bank at church, causing my 3 year old to ask, ā€œDaddy, do pigs have banks?ā€ As I think about this, it gets even more puzzling, because I'm not sure he's ever been to a bank.