Re:How can we be sure AI will behave? Perhaps by watching it...
by EGreg on Tuesday May 15, 2018 @09:51AM
(#17073894)
People underestimate MCTS greatly
It beat Rybka and every other bespoke chess program in existence
AlphaZero even beat the version of AlphaGo that was trained on existing data.
Point is — we have no idea what is possible when you unleash MCTS towards goals like persuasion, humor etc.
The ONLY constraint here is that feedback requires a human judge. If you can learn to simulate a human based on lots of data (this is a hard part) then you can finally have a two sided game playing each other and find the best diets, the best diagnoses utilizing symptoms, tests and big data around the world of incidence of outbreaks etc.
However it also means quickly finding the funniest jokes, most convincing but subtly flawed arguments, best artworks etc.
It beat Rybka and every other bespoke chess program in existence
AlphaZero even beat the version of AlphaGo that was trained on existing data.
Point is — we have no idea what is possible when you unleash MCTS towards goals like persuasion, humor etc.
The ONLY constraint here is that feedback requires a human judge. If you can learn to simulate a human based on lots of data (this is a hard part) then you can finally have a two sided game playing each other and find the best diets, the best diagnoses utilizing symptoms, tests and big data around the world of incidence of outbreaks etc.
However it also means quickly finding the funniest jokes, most convincing but subtly flawed arguments, best artworks etc.