- anything that goes deep into issues (I seldom read “i love llms” type posts like this is great: https://blog.nilenso.com/blog/2025/09/15/ai-unit-of-work/)

- lots of experimentation - specifically I have spent hours and hours doing the exact same feature (my record is 23 times).

- if something “doesn’t work” I create a task immediately to investigate and understand it. even the smallest thing that bother me I will spend hours to figure out why it might have happened (this is sometimes frustrating) and how to prevent it from happening again (this is fun)

My collegue describes the process as Javascript developer trying to learn Rust while tripping on mushrooms :)