Ask HN: Does per-second billing make sense for GPU Instance?

		Ask HN: Does per-second billing make sense for GPU Instance?
		1 point by nogox on Aug 10, 2017 \| hide \| past \| favorite
		Assume that you can provision a GPU instance in EC2 in 10 seconds, and they charge you by seconds, not hours. Does this make sense to your AI/ML project? If the job takes hours or days to finish?