alt Hacker NewsI resonate with that. I also find writing code super pleasurable. It's immediate stress relief for me, I love the focus and the flow. I end long hands-on coding sessions with a giddy high.
What I'm finding is that it's possible to integrate AI tools into your workflow in a big way without giving up on doing that, and I think there's a lot to say for a hybrid approach. The result of a fully-engaged brain (which still requires being right in there with the problem) using AI tools is better than the fully-hands-off way touted by some. Stay confident in your abilities and find your mix/work loop.
It's also possible to get a certain version of the rewards of coding from instrumenting AI tools. E.g. slicing up and sizing tasks to give to background agents that you can intuit from experience they'll be able to actually hand in a decent result on is similar to structuring/modularization exercises (e.g. with the goal to be readable or maintainable) in writing code, feelings-wise.
Replies
I'm in the enjoy writing code camp and do see merits of the hybrid approach, but I also worry about the (mental) costs.
I feel that for using AI effectively I need to be fully engaged with both the problem itself and an additional problem of communicating with the LLM - which is more taxing than pre-LLM coding. And if I'm not fully engaged those outcomes usually aren't that great and bring frustration.
In isolation, the shift might be acceptable, but in reality I'm still left with a lot of ineffective meetings - only now without coding sessions to clear my brain.
I get a dopamine hit with AI by being able to accomplish tasks fast, mostly in frontent or using a dynamic language like python because you see the changes in real time