This article articulates a lot of how I feel about using AI today. I can see that I will use it more, but I don’t know yet how to use it more while maintaining the level of understanding of the code I want to retain.
I attempt to set a high bar for what I want code to look like, and I want to understand the code I ship. Under pressure, or in a discussion with another human, I want to be able to explain what the system does without first having to ask [an ai model] to explain it to me. Now there is obviously a question if this desire to understand the code is one that I will still have a few years from now. For now I have not moved past the point of comprehension being important to me.
Given this desire, there is something I lack with my experience of code written without me paying attention, particularly from loops. Present-day models tend to produce code that is too defensive, too complex, too local in its reasoning. […] At least for my taste, present-day hands-off harnesses like Claude Code with ultracode produce worse code than what we were producing last autumn. That’s because Claude Code, with Fable for instance will be working uninterrupted on a problem for thirty minutes or more, when previously the process would have been much more human in the loop.