I can see that others might not like it, but this is the behavior I desire.

▲ wjnc 11 hours ago | parent | next [-]

I enjoy risk seeking behavior as well as the next guy, but lets please be adults and make this opt-in, not opt-out. If you get the LLM to ask the right questions, (for me) obviously you would want it to wait for an answer?

	▲	solenoid0937 11 hours ago \| parent [-]
		This isn't "risk seeking" in the least, it's not a security thing. You can always come back later if the design was wrong - you can't undo 7 wasted hours because you didn't notice an agent ask a question at the beginning of the day. A year ago everyone thought that humans should review every agent command before executing them. Every major company realized that was dumb and now most enterprise agents run in a sandbox without being babysat. This is just an extension of the same principle. As models get better you can trust them to make the right architectural choice more often. The likelihood of a human missing a prompt or not wanting to babysit the agent is higher than the agent choosing the wrong option.

▲ Guillaume86 11 hours ago | parent | prev | next [-]

Just prompt it that way then, I can get Claude to plow through features for 12h with the correct prompt and setup, no need to destroy the tools that are useful when you want the opposite.

▲ ares623 11 hours ago | parent | prev | next [-]

Then why even ask the question if the answer wasn't needed?

▲ petesergeant 11 hours ago | parent | prev [-]

In a way that isn't configurable and is on by default?

▲ ninju 11 hours ago | parent [-]

Reading the comments on the issue shows how to configure it

  "env": {
    "CLAUDE_AFK_TIMEOUT_MS" : "<massive number>"
  }

https://github.com/anthropics/claude-code/issues/73125#issue...

	▲	whateveracct 11 hours ago \| parent [-]
		so there's a hack to disable it