Comment by bob1029
6 days ago
I am finding the most destructive aspect of LLM assistance to be the loss of flow state.
Most of the time I can go faster than these tools if I have confidence in myself and allow the momentum to build up over the course of 20-30 minutes. Every time I tab out to an LLM is like a 5 minute penalty over what I could have done unaided on a good day.
Getting the model prepared to help you in a realistic domain often takes a few minutes of arranging code & comments so that it is forced toward something remotely sane. I'll scaffold out entire BS type hierarchies just so I can throw a //TODO: .... line in the middle somewhere. Without this kind of structure, I would be handling unfiltered garbage most of the time.
It's not that these tools are bad, it's that we need to recognize the true cost of engaging with them. ChatGPT is like a jackhammer. It will absolutely get you through that concrete slab. However, it tends to be quite obnoxious & distracting in terms of its operational principles.
> I am finding the most destructive aspect of LLM assistance to be the loss of flow state.
Finally someone else mentions Flow!
I find the opposite, I can stay in flow state much longer than I could before because tabbing out to an LLM is a tighter loop than me going out to google and searching through sites for smaller tidbits that I have to assemble and get through, rather than a full solution that might not be 100% correct, but most of the time I can get to the working solution quicker.