Yeah, you've exactly captured one of the main problems with the model being relentlessly proactive: it will happily burn like $5 of tokens to avoid asking the human to take a screenshot or click a button for it.
Giving it access to a cheap human who is just there to take screenshots, do QA, give UX feedback sounds like a good idea in principle. It's non-trivial to set up, but I wouldn't be surprised if some companies this becomes a thing. The return of the QA department, just that they now get to do the agent's bidding in addition to checking if the results work
I eventually just accepted it, but this new agent layer really takes things to a new level.
I wonder if LLMs can estimate effort in tokens?
Like today, I told Claude exactly the name of the folder it had mistaken (it was supposed to be prod, not production), and it disregarded my input to then examine the directory itself. Small example of the kind of things it's been doing lately but that's top of mind.