Hacker News new | past | comments | ask | show | jobs | submit
elevation | on: Workers are spending over 6 hours a week botsitting AI, fueling job frustration
> sandbox so that the agent doesn't keep asking tedious permission questions

> 80% of the questions the agent asks me require a lot of thought. 20% of what it does needs correction.

I've found even the permissions questions give me veto power over fruitless lines of exploration, especially in planning mode. For instance, it wants to use tools I don't have installed to access information that I have made available elsewhere? I get a chance to override this decision by declining the permissions check and redirecting it. Feels tedious, but helps me understand what information sources are influencing it. I head off a lot of bugs this way.

kstenerud | parent | next
I never let it go into planning mode, other than to output a plan file that I can audit before giving it the go-ahead to implement. After that I don't want to be bothered, so --dangerously-skip-permissions keeps all but real questions out of the loop, and I can do something else while it works rather than babysit.
kqr | parent
This is my impression too. Whenever it needs permissions outside of a small set of defaults I've allowed, it's often because it's trying to do something ridiculous that it doesn't need to do.

I think the yoloist counter-argument is "So what? Let it. It'll take longer that way and consume more tokens, but you can work on something else in parallel instead of being hooked in to this one session".