Home
Creators
Search Recent Random
Posts
Search DMs Popular Hash Lookup Tags Random
Importer
Import FAQ
Register Favorites Keys Review DMs Logout
Community
Telegram ThePornDude
Home Creators Posts Import Register Favorites Logout

Is AI Safety a Pascal's Mugging? (Patreon)

Published:
2019-05-14 15:55:22
Imported:
2026-06
Tags:
haven't archived this post yet. have a subscription? use the importer!

Content

An event that's very unlikely is still worth thinking about, if the consequences are big enough. What's the limit though?

Do we have to devote all of our resources to any outcome that might give infinite payoffs, even if it seems basically impossible? Does the case for AI Safety rely on this kind of Pascal's Wager argument? Watch this video to find out that the answer to these questions is 'No'.

https://youtu.be/w03_ATCGQQM

Edit: In light of your ideas and suggestions, I've updated this video slightly for the main release, which is here: https://youtu.be/JRuNA2eK7w0

Files

Previews only

Is AI Safety a Pascal's Mugging?

An event that's very unlikely is still worth thinking about, if the consequences are big enough. What's the limit though? Do we have to devote all of our resources to any outcome that might give infinite payoffs, even if it seems basically impossible? Does the case for AI Safety rely on this kind of Pascal's Wager argument? Watch this video to find out that the answer to these questions is 'No'. The Alignment Newsletter Podcast: http://alignment-newsletter.libsyn.com/ With thanks to my excellent Patreon supporters: https://www.patreon.com/robertskmiles Jason Hise Jordan Medina Scott Worley JJ Hepboin Pedro A Ortega Said Polat Chris Canal Nicholas Kees Dupuis Jake Ehrlich Mark Hechim Kellen lask Francisco Tolmasky Michael Andregg James Richárd Nagyfi Phil Moyer Shevis Johnson Alec Johnson Lupuleasa Ionuț Clemens Arbesser Bryce Daifuku Allen Faure Simon Strandgaard Jonatan R Michael Greve Julius Brash Tom O'Connor Erik de Bruijn Robin Green Laura Olds Jon Halliday Paul Hobbs Jeroen De Dauw Tim Neilson Eric Scammell Igor Keller Ben Glanton Robert Sokolowski anul kumar sinha Jérôme Frossard Sean Gibat A.Russell Cooper Lawton Tyler Herrmann Tomas Sayder Ian Munro Jérôme Beaulieu Gladamas Sylvain Chevalier DGJono robertvanduursen Dmitri Afanasjev Brian Sandberg Marcel Ward Andrew Weir Ben Archer Scott McCarthy Kabs Tendayi Mawushe Jannik Olbrich Anne Kohlbrenner Jussi Männistö Mr Fantastic Wr4thon Archy de Berker Marc Pauly Joshua Pratt Andy Kobre Brian Gillespie Martin Wind Peggy Youell Poker Chen Kees Truls Paul Moffat Anders Öhrt Marco Tiraboschi Michael Kuhinica Fraser Cain Robin Scharf Oren Milman John Rees Seth Brothwell Brian Goodrich Kasper Schnack Michael Hunter Klemen Slavic Patrick Henderson Long Nguyen Melisa Kostrzewski Hendrik Daniel Munter Graham Henry Volotat Duncan Orr Bryan Egan James Fowkes Frame Problems Alan Bandurka Benjamin Hull Dave Tapley Tatiana Ponomareva Aleksi Maunu Michael Bates Simon Pilkington Dion Gerald Bridger Steven Cope Petr Smital Daniel Kokotajlo Joshua Davis Fionn Tyler LaBean Roger Yuchong Li Nathan Fish Diagon Giancarlo Pace https://www.patreon.com/robertskmiles

Comments

loopuleasa

Interesting perspective. I never drew the link between AI claims and Pascal's claims. There is a small similarity of traits. Humans in general are bad at estimating probabilities and dealing with them. Just look at the well-documented "possibility bias" and the "what you see is all there is" principle. Thinking Fast & Slow, and The Black Swan and Fooled By Randomness are good books on this topic. I agree with your thesis here, that we have to reason from first principles on issues like this to not go extinct or obsolete as a species. As a whole lifeform really (DNA replicators)

Branislav Konjevic

I know that this isn't the right moment to talk about this - but I just found this channel, and I have to comment on a subject of reward hacking. There's another critical aspect of this thing - the human side of the story. It's well known how the brains are lazy, and after a vastly superior AGI is created (assuming that we create it without the problems)- there will be no need for human intelligence. Do we want to be a bunch of morons watching all day as some robotic creatures entertain us? Where's the thing that defines humanity? I wouldn't like to change myself in this direction. Don't forget, also that we humans don't like when somebody is vastly smarter than us. I would rather like that an idea of making humans smarter prevails. We can do that by connecting our brains wirelessly, and I hope that this will come sooner then AGI.