News for hackers. Stuff that matters.

A comment on OpenAI Charter. Parent comment

Re:OpenAI Charter by p1esk on Monday April 09, 2018 @05:01PM (#16796960)
Do you think limiting research on recommender systems (or limiting access to such research) would help in this case?

What would be a solution to YouTube recommendation problem?

[ Parent | on HN ]
Re:OpenAI Charter by colah3 on Monday April 09, 2018 @05:12PM (#16797054)
It seems like OpenAI's Human Feedback research (in collaboration with DeepMind) is targeted at this sort of thing. They try to use human feedback to create more nuanced and aligned objectives.

https://blog.openai.com/deep-reinforcement-learning-from-hum...

[ Parent | on HN ]