Then you miss the point - AI use is being compared to gambling because it is addictive, partly due to same mechanism - the results (and rewards) are somewhat random, but it makes you feel as if you're completely in control of the outcome.

Strange. I tell Claude Code to do things differently all the time.

I'd recommend a different workflow, with extensive upfront planning. This works extremely well for me:

https://www.stavros.io/posts/how-i-write-software-with-llms/

It's to the point that I just push the output of that to production and know it'll be OK, except for very large changes where I'm unlikely to have specified everything at the required level of detail. Even then, things won't so much be wrong, as they'll just not be how I want them.

Thank you for sharing this. It is weirdly encouraging to see someone take a path similar to mine.