AI Safety Gym - Computerphile
119,436
Published 2020-01-30
Rob Miles discusses the idea of a gym for training AI algorithms.
www.facebook.com/computerphile
twitter.com/computer_phile
This video was filmed and edited by Sean Riley.
Computer Science at the University of Nottingham: bit.ly/nottscomputer
Computerphile is a sister project to Brady Haran's Numberphile. More at www.bradyharan.com/
All Comments (21)
-
"A ship in harbor is safe — but that is not what ships are built for."
-
Awesome. I’ve watched literally everything Rob has recorded on AI. He’s very relatable, knowledgeable and informative.
-
Miles is an excellent teacher. Always does a great job fielding questions from a layperson.
-
Rob's video on the 3 laws of robotics is what really demonstrated to me how serious ai safety really is.
-
Looks like they're taking security very seriously. This guy is always kept inside a prison to avoid his rogue AI pets from escaping.
-
I used to know this guy. Glad he’s still at it. Easily one of the smartest dudes I’ve met in person
-
7:58 that artificial camera movement is both trippy and impressive!
-
The sponsor intro is too loud. Edit: as is the sponsor segment at the end.
-
never knew notts uni had a prison to film in
-
I'm a man of simple tastes - I see Rob Miles, I press the like button.
-
I like the fact that young Robert uses the same Simpsons references I remember from 20-odd years ago
-
I really love listening to Rob's explanations.
-
Fab and super interesting video, also v. much appreciated your [Rob's] EA talk yesterday - will definitely be checking out the AI Safety field in more depth.
-
enable subtitles please
-
I initially read this as "AI Sentry Gun" and thought Rob was having a crisis.
-
Completely agree. Big safety failures - in organisation structure, or real world industry, or whatever - usually occur because of either unknown elements in the environment or unexpected interaction by known elements. Because - at stupidly obvious level - if you could predict it you would (you'd hope) have done something about it. Thanks for the the description on the constraint learning. Keeping constraints and goals kept as modular elements is one of those things that makes obvious sense once someone explains it to me.
-
13:39 😂 I love how they named all these thing
-
Sneaky hitch hikers reference ;) love it!
-
Could you link paper?
-
I wonder if you can get complicated multidimensional shapes like optimization problems for reward functions