I think part of the problem is that the Big Ai labs are into the --yolo flag instead of the "ask" permission, they really do not want to stay in the loop

▲

jchw 4 hours ago | parent [-]

You can --yolo if your security boundary is a serious one, IMO. Although it's really only actually scary if you're running some absurd 1000 node swarm.

	▲	verdverm 3 hours ago \| parent [-]
		the problem at the labs is likely Recursive Yolo Development and not reading any of the output