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.
[ Parent
| on HN ]
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.