[vidarh]

My point is that these are not minor successes, and not occasional. Not every attempt is equally successful, but a significant majority of my attempts are. Otherwise I wouldn't be letting it run for longer and longer without intervention.

For me this isn't one project where I've "twiddled around with the file and added random sentences". It's an increasingly systematic approach to giving it an approach to making changes, giving it regression tests, and making it make small, testable changes.

I do that because I can predict with a high rate of success that it will achieve progress for me at this point.

There are failures, but they are few, and they're usually fixed simply by starting it over again from after the last succesful change when it takes too long without passing more tests. Occasionally it requires me to turn off --dangerously-skip-permissions and guide it through a tricky part. But that is getting rarer and rarer.

No, I haven't formally documented it, so it's reasonable to be skeptical (I have however started packaging up the hooks and agents and instructions that consistently work for me on multiple projects. For now, just for a specific client, but I might do a writeup of it at some point) but at the same time, it's equally warranted to wonder whether the vast difference in reported results is down to what you suggest, or down to something you're doing differently with respect to how you're using these tools.