Post #4278288

2026-07-29 21:18 UTC

@jonny@neuromatch.social what worked in my own experiment was giving the harness a stack of explorations with defined success criteria what i got was a microkernel that met defined success criteria but had poor design. in fact, at one point, its refusal to code proper data structures forced me to interrupt it and give it an immediate task of writing a real red-black tree for my own sanity. i didn't like the experience. it was amusing, but not any way i would ever want to write real software.

Replies (1)

@jonny@neuromatch.social 2026-07-29 21:26

@ariadne@social.treehouse.systems that's also the only way i've ever gotten it to do plausible work for things where that is definable, to already have a handwritten set of tests that define completion, and i've seen people say that's how they work as an evolution of TDD. for something like a game this simple i usually wouldn't even write tests except the most obvious regression tests for "the game still works". thinking about how to test it would be almost as complex as the game itself. i also agree about this not being how i would want to work in general - this has been a joyless endeavor that feels more like addiction than problem solving. the only place it "improves" over just writing the damn thing myself is that it required a hell of a lot less cognitive effort and thinking, but that... is... the fun part...

Open ##4299470