9 min listen
Reinforcement Learning Gone Wrong
ratings:
Length:
28 minutes
Released:
Jul 11, 2016
Format:
Podcast episode
Description
Last week’s episode on artificial intelligence gets a huge payoff this week—we’ll explore a wonderful couple of papers about all the ways that artificial intelligence can go wrong. Malevolent actors? You bet. Collateral damage? Of course. Reward hacking? Naturally! It’s fun to think about, and the discussion starting now will have reverberations for decades to come.
https://www.technologyreview.com/s/601519/how-to-create-a-malevolent-artificial-intelligence/
http://arxiv.org/abs/1605.02817
https://arxiv.org/abs/1606.06565
https://www.technologyreview.com/s/601519/how-to-create-a-malevolent-artificial-intelligence/
http://arxiv.org/abs/1605.02817
https://arxiv.org/abs/1606.06565
Released:
Jul 11, 2016
Format:
Podcast episode
Titles in the series (100)
Computers Try to Tell Jokes: Computers are capable of many impressive feats, b… by Linear Digressions