jprokay13

I think pi-mono (https://github.com/badlogic/pi-mono) is pretty close. The extensibility is wonderful and a much better fit for how I work compared to Claude Code.

https://jprokay.com

Goal for the year is to post every two weeks

I’m in a similar boat. Many artists I listen to on Bandcamp offer cassettes(!) at a fair price and will charge a comparable price for the digital. However, I’ve seen some artists charge thousands for digital only but $10 for a tape that includes the digital version.

I don’t know why they do this, but I do know I have an ever growing stack of tapes I can’t listen to…

  yet again I reached for a dependency when Postgres is enough

I’m debating Typesense vs. Meilisearch for a project. My use case isn’t particularly complex so either fits.

Curious if anyone has any horror stories about either

I am still working on tweaking how I work and design with Claude to hopefully unlock a level of output that I’m happy with.

Admittedly, part of it is my own desire for code that looks a certain way, not just that which solves the problem.

I am coming back to this. I’ve been using Claude pretty hard at work and for personal projects, but the longer I do it, the more disappointed I become with the quality of output for anything bigger than a script. I do love planning things out and clarifying my thoughts. It’s a turbocharged rubber duck - but it’s not a great engineer

At first I thought becoming “10x” meant outputting 10x as much code. Now that I’m using Claude more as an expensive rubber duck, I’m hoping that I spend more time defining the fundamentals correctly that will lead to a large improvement in outcomes in the long run.

Why look to the past when you can rediscover it from “first principles?” /s

My personal experience was that of a decrease in productivity until I spent significant time with it. Managing configurations, prompting it the right way, asking other models for code reviews… And I still see there is more I can unlock with more time learning the right interaction patterns.

For nasty, legacy codebases there is only so much you can do IMO. With green field (in certain domains), I become more confident every day that coding will be reduced to an AI task. I’m learning how to be a product manager / ideas guy in response

What’s the best way to stay informed about the typescript version?

Neat! I am going to check this out. I recently built an MCP system similar to this called Nonlinear (so clever) that uses SQLite for storage that lives outside the repo. Honestly though, in repo is the better option.

Claude recommended I use Tilt for setting up a new project at work. I wasn’t sure if it was worth it…is it pretty easy to set up a debugger? Not only do I have to adopt it, but I have to get a small team to be OK with it.

Our target deploy environment is K8S if that makes a difference. Right now I’m using mise tasks to run everything

Yeah I find it pretty funny that so much of us (myself included) threw out strict documentation practices because “the code should be self documenting!” Now I want as much of it as I can get.

If you haven’t, adding in strict(er) linting rules is an easy win. Enforcing documentation for public methods is a great one imo.

The more you can do to tell the AI what you want via a “code-lint-test” loop, the better the results.

Create a file like conventions.md in the root of your repository with specific commands for common tasks: running tests, linters, formatters, adding packages Set this as part of the files it reads on startup. Then ask aider to look at your codebase and add to it :) Aider has a lot of slash commands to familiarize yourself with. Ask and web are crucial commands to get the most out of it.

My recommendation to anyone is to use ask the most then tell it to “implement what we discussed” when it looks good.

Hope that helps

I’ve been floating around a similar set of ideas and it’s been very fun (if not all that useful yet) to build Did you try taking it one step further where a “recruiter” has to hire the engineers after a screening process? I wonder if this could get you even better AI engineers

I built a web app for looping specific sections of YouTube videos as a way to practice songs.

https://proloops.jprokay.com/

Slowtube was a huge inspiration for me (I’ve spent many hours with it), but I wanted a way to save my loops and continue my practice.

Saving is solely to the browser’s database right now.

Feedback is much appreciated!

Do you have any recommendations on how to get started with Keycloak or just RTFM?

Yeah that was what I was afraid of. I thought I saw in the caddy code that they did a sort on file name, but I must have misread it. Thanks for responding!

Edit: after looking more closely at sprig, the solve was sortAlpha

I went all in on using Caddy for rendering my website and blog, but I’m encountering a frustrating issue that I’m not sure how to solve. The feed on my site uses the listFiles feature to populate from a directory. I take care to name things so ordering is preserved. No problems on my machine getting the feed ordered correctly. However, when deployed to Railway via a container, the ordering is all wrong. Any thoughts on how to debug?

For a long time I used an app called Slowtube to practice guitar. I recently built my own version with features I always wanted like the ability to save sections of songs for future practice, search YouTube (instead of copying links), and provide cross device synchronization. I’m using it daily for practice now and after a bit of polish I plan to put it up on my website

I recently set up a conventions.md file for Aider along with configuring sonnet 3.7 with reasoning.

It really was another leap forward for me with AI. Using it for exploratory analysis of solutions is the best rubber duck I’ve ever had

We recently completed an ADU project in California and figuring out the financing was particularly difficult. Add on additional requirements like mandatory solar, fees on top of fees ($5000 school impact fee was just one of many), a local building department with one person reviewing everything… It’s not an easy undertaking at all!

Many of the founders I know (who started companies in the past 3 years) are primarily hiring in LATAM too.

If you are going after enterprise early, I highly recommend putting them on their own system instead of in a multi-tenant system. Enterprise wants 30 days of immutable db backups? They need to be able to rollback within X time? They want guarantees that other people won’t affect them?

This all becomes easier if you turn it from an engineering problem to an operations problem. Enterprise really cares about how you operate in order to guarantee they won’t be negatively impacted by your system. SOC2 is much more about your operations than anything else.

My recommendation: have a multi-tenant system for the plebs and bespoke deployments for the enterprise. Save yourself the headache of trying to satisfy both with the same infrastructure.