I am now using agentic coding quite a lot. The honeymoon is finishing and I am starting to dislike some facets of it. I think the main setback is the rythm.
Writing some specs/prompts, launching the agent, confirming quite atomic actions and waiting 10 to 30 seconds until the next question/confirmation. Those very small wait times do not let me reach a concentration state.
I feel I am hovering the code. I am not deep into it as I used to be.
Do you feel the same? Did you find a way to change this?
But the broken rhythm problem persists regardless, and I find that issue to become more and more serious as LLMs are able to work for longer and longer on their own.
It might be that what we're experiencing now is just an uncanny valley, where they're not yet good enough for us managing them to work in similar ways as with other developers, but are good enough to allow us to switch our attention away from them while they work. But that attention span is mostly wasted, as the time between interactions isn't enough to e.g. work on something else, or read a book.
It's a stupid analogy, but currently it's similar to having a bathroom break every couple of minutes, and if this continues, most developers will probably start doomscrolling more and more.
I was wondering recently if there are some productive activities that might fit well into this rhythm, but I haven't found any yet. I guess sourdough baking is one such example, but there's only so much bread you can eat...
I feel the solution is either reduce drastically time between each interaction with the agent OR increase it by a lot (every 2 or 3 hours).
Maybe we do not have the right workflow yet. Maybe the work with an agent should be more async.
I guess we will figure out.
The other times, when I let it generate 3k LOC with minimal supervision, yeah, that's when I die inside.