fkozlowski

So actually I've been testing this — it seems to be useful in limited cases. LLMs have gotten so good now that a properly defined spec is no worse than a spec + property based testing.

I still found it useful for

1. trusting a bit of code is correct

2. rule-dense bits of code (eg something like a date parser)

The real issue so far is that I'm having trouble finding tasks where an LLM can't correctly code up an exhaustively defined spec.

It's a great way to rebuild a sense of agency for me. I find the weekend binge a good way to feel like I can effect changes in the world.

Nice! It's interesting to see quantitative ways of measuring slop. I'm curious what _would_ happen if you did plug these back into the LLM as a form of feedback. Goodharting may happen... or it could get the LLM to generate cleaner code potentially?

MASCA has a ring to it!

Agreed — I also always append to my agents.md — "If there are any technical choices available, please surface them to me so I can understand them and choose"

I find that it's difficult to thread the needle of navigating on my own with also not spending forever in traffic or in train delays. It's disheartening when I do know how to get somewhere, but I land in a +1 hour traffic jam because I chose to not look at GPS.

Maybe I need an app that just yells at you when you take a super-wrong turn, or if you're about to be in a massive amount traffic?