I am wondering if working with agentic AI for 500+ hours built up skills for this.
While I would feel rusty when handwriting code, working with either Codex or Claude I have lots of practice.
I can probably tell at a glance where output is intermediate while it's still running tools and where the summary starts.
Then I have to recall the context of the conversation, parse the summary, see if there is anything unexpected that popped up. Make a call for whether I need to ask it for clarifications, and what I need to test to verify the change.
Assessing quickly what is pointless yapping and where the information I need is might be a learned skill. If one tries to read and understand every word Claude says, I am not surprised that people are not having a good time.
While I would feel rusty when handwriting code, working with either Codex or Claude I have lots of practice.
I can probably tell at a glance where output is intermediate while it's still running tools and where the summary starts.
Then I have to recall the context of the conversation, parse the summary, see if there is anything unexpected that popped up. Make a call for whether I need to ask it for clarifications, and what I need to test to verify the change.
Assessing quickly what is pointless yapping and where the information I need is might be a learned skill. If one tries to read and understand every word Claude says, I am not surprised that people are not having a good time.