Posts

Comments

Comment by Razvan Ciuca (razvan-ciuca) on What Evidence Is AlphaGo Zero Re AGI Complexity? · 2017-10-23T00:35:02.554Z · LW · GW

If Deep Learning people suddenly starting working hard on models with dynamic architectures who self-modify (i.e. a network outputs its own weight and architecture update for the next time-step) and they *don't* see large improvements in task performance, I would take that as evidence against AGI going FOOM.

Comment by Razvan Ciuca (razvan-ciuca) on What Evidence Is AlphaGo Zero Re AGI Complexity? · 2017-10-22T16:08:04.252Z · LW · GW

As far as I can see you can use the same techniques to learn to play any perfect information zero-sum game