Activity Feed

I think you defeated my criticism. That’s kind of cool, I get it.

This could extend beyond fixing errors to improving page load times, search quality, and reducing churn, provided you can measure whether a change helped. My friend Samay co-wrote this about a similar loop using production feedback and evals to improve tax agents:
https://openai.com/index/building-self-improving-tax-agents-with-codex/

Kitty Comes Home: my first game made with Claude Opus 5.5.

You play as a little kitten trying to find your way back to your mom.

Play for free here: https://blog.dennishackethal.com/posts/kitty-comes-home

Teaser trailer: https://youtu.be/bcM2BI-41cY

Midnight Ride: Production Errors That Fix Themselves (Almost)

blog.dennishackethal.com

Midnight Ride: Production Errors That Fix Themselves (Almost)

Midnight Ride, my new Rails gem, sends production errors from Solid Errors to Telegram and starts a Claude Code session that opens a PR with the fix.

It doesn’t play the whole codebase at once. It walks through the code line by line, and when a file changes, it jumps to the changed lines and plays an accent made from them, rising or falling with that file’s health. So a small change in a big codebase is as audible as one in a small codebase. What’s quieter in a big codebase is the overall stage, and that’s on purpose: one long function shouldn’t make a whole healthy codebase sound sick. Bugs are the exception, since they count in full. One syntax error drops even a huge project from beautiful to meh.

Relatedly, I think in the future, software engineering will mostly be you talking to voice agents and looking at diagrams the agent is generating and constantly updating to help you understand the code/ideas. This is kind of how students already learn in the classroom, where there's a teacher who talks them through a drawing on the board, etc.

 It responds live as you make changes to your code

This seems useful only for small codebases. If the music is composed of all the code in a large codebase, each PR would change only a small subset, making the difference in the music almost inaudible.

Quote Checker now supports MLA and APA style guides, helping you quote more accurately:

quote-checker.com

Quote Checker · Your Home for All Things Misquotes

Quote people the way they actually said it. Compare a quote with its original and see every change that isn’t marked.

What If You Could Hear Your Code?

blog.dennishackethal.com

What If You Could Hear Your Code?

Synesthete is a free Sublime Text package that turns your code into music, so you can hear its quality – and every change your coding agent makes.

Understanding in the Age of AI:

libertythroughreason.com

Understanding in the Age of AI

Why serious epistemologists must be programmers, and whether vibe coding with AI counts as understanding. Takeaways from my Conjecture Con 2026 talk.

Apparently Scribd profiles are public? 🤷‍♂️ https://www.scribd.com/user/430906064/Dennis-Hackethal

A single additional day won’t cause much strength loss, if any.

I may still know depending on the numbers. If my strength dips a lot, then it’s not plausibly due to poor sleep (I didn’t sleep that poorly) and I should ease up on the cut anyway.

But knowing I’m losing muscle would inform my decision about stopping the cut sooner.

I’ll be on the cut for another week at least, so there’ll be one more workout to compare with. Not everything hinges on today or tomorrow.

I’ve been sleeping poorly in general lately. Who’s to say tonight’s sleep will be better? It may even get better because I work out today.

Wrong parent.

But if I still hit PRs while on aggressive cut and having slept poorly, that data point would be all the more meaningful for it.

I’ve been sleeping poorly in general lately. Who’s to say tonight’s sleep will be better?

Okay but if I go tomorrow and I do lose strength, I won’t know if it’s because I waited too long.

But this is the first time I’m doing a cut this aggressive for more than just a week. I’m approaching the two-week mark. I know eventually I won’t be able to maintain strength, but it would still be good to know where the cut-off point is, roughly.

I’ve gone to the gym twice already during this cut and kept my strength each time, even hit PRs on some exercises. And last time I did this cut I also hit PRs.