News for hackers. Stuff that matters.
Re:Learning from Human Preferences by RepressedEmu on Tuesday June 13, 2017 @12:13PM (#14545882)
Its doing a frontflip not a backflip but I guess thats secondary to how efficient this kind of human-AI collaboration might turn out to be. Similar in vein to the human-AI "centaur" chess teams.
Re:Learning from Human Preferences by nategri on Tuesday June 13, 2017 @06:24PM (#14549181)
Extending the concept of 'front' and 'back' to a vertical pile of hotdogs is a separate, but relevant, problem.
Re:Learning from Human Preferences by RepressedEmu on Monday June 26, 2017 @03:13PM (#14639419)
Good point. I guess i just anthropomorphized the pile of hotdogs the wrong(mirrored) way compared to the researchers.