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

AMA | i taught an AI to solve the trolley problem (Patreon)

Published:
2021-06-11 20:33:25
Imported:
2026-06
Tags:

Content

New video went live today. Director's commentary is uploading. Do y'all have any questions about this video - from research, content, to technical details - ask me anything in the comments and I'll do my best to answer :)

Files

i taught an AI to solve the trolley problem

The first 1000 people to use the link will get a free trial of Skillshare Premium Membership: http://skl.sh/answerinprogress06211 Can you teach a machine to be a good person? In this video, Sabrina explores the world of AI ethics and tries to teach a machine to solve the trolley problem. It doesn't go well. SUBSCRIBE TO OUR MONTHLY NEWSLETTER https://www.answerinprogress.com/newsletter FULL INTERVIEWS Dr. Tom Williams: https://youtu.be/PVpNi0yJCTo Deborah Raji: https://youtu.be/w4smn7xrbik Podcast Version: https://open.spotify.com/show/4O9zacVfkOMbxxMFjfkxX4 SOCIAL MEDIA Sabrina Twitter: https://twitter.com/nerdyandquirky Instagram: http://instagram.com/nerdyandquirky Melissa Twitter: https://twitter.com/mehlizfern Instagram: http://instagram.com/mehlizfern Taha Twitter: https://twitter.com/khanstopme Instagram: http://instagram.com/khanstopme CREDITS Produced by Sabrina Cruz Video Editing by Joe Trickey Motion Design by Sabrina Cruz Special Thanks to Brittany Palandra Chase Madsen (https://twitter.com/ChaseVsEvrythng) Deborah Raji (https://twitter.com/rajiinio) FootofaFerret (https://twitter.com/FootofaFerret) Gabrielle Agustin Jade Codinera Jordan Balke (https://twitter.com/SuperAwesomeJEB) Jordan Harrod (https://twitter.com/JordanBHarrod) Keslen Murdock Matthew Gaydos (https://twitter.com/MatthewGaydos) Melissa Fernandes (https://twitter.com/mehlizfern) Mikaela Palandra Tierzoo (https://twitter.com/TierZoo) Dr. Tom Williams (https://twitter.com/williamstome) Travis Gilbert (https://twitter.com/TravisoGilbert) Xi Huang MUSIC Epidemic Sound. Get started today. http://share.epidemicsound.com/answerinprogress TIMESTAMPS 00:00 in before sabrina accidentally causes the singularity 00:32 what is the trolley problem? 01:10 i would like to fight the trolley problem 01:40 why does sabrina look like an a24 film boy? 02:00 congratulations if you immediately recognized that this was a bad idea 02:51 ending friendships, a montage 04:40 how to solve the trolley problem (with a robot) 05:58 sabrina still doesn't know how to use pandas 06:10 uh oh 06:39 What Went Wrong? A Game Show 08:45 What Went Wrong? The Sequel 09:22 The Three Waves of AI Ethics | 13:38 Autonomous Vehicles and the Trolley Problem 16:07 forget the past 16 minutes of your life 16:24 paying the bills ------------------------------------------------------------------------------------ Welcome to the joke under the fold! Speaking of philosophical journeys... Why do marine biologists make good philosophers? Because they spend their lives search for porpoise. Leave a comment with the word PORPOISE to let me know you were here ;-)

Comments

Joshua Staton

Did you have any discussions about the difference between an ethical AI and a Human like AI? Essentially humans do a lot of unethical things, even small things in day to day life. Would your goal be for the AI to make decisions like a human or purely the most ethical decision?

Sabrina Cruz

While researching, I definitely considered the differences in approach - do I create an "objectively" virtuous machine that follows a doctrine of my choosing VS do I create a machine that mimics that acts of relatively ethical people. I ended up choosing the latter because (1) on a theory level, I'm not well-versed enough to pick "the best moral philosophy" let alone create a value system that encompasses that domain well enough for a machine to be able to use it to make decisions and (2) if I was able to do that, implementing that knowledge is currently outside the scope of my ability. I would've needed to figure out how to do reinforcement learning on top of everything else. It's definitely a technique I want to pick up for future videos though - might make an AI to learn chess so I don't have to :) - Sabrina

Joshua Staton

That's fair enough. What you were able to create is still pretty impressive! And imo, I don't think the cat problem was really a problem at all. :P So then the obvious follow up question, and this might be too big of a question so no worries if you don't have an answer, if you were able to create a purely objectively ethical AI, should we? It would probably make decisions that we wouldn't agree with, but would that make those decisions wrong? For instance, maybe there are 10 people aged 80 on one track, and 1 person aged 10 on the other track. The AI might conclude that there are more years of human experience left on the second track and kill the 10 people.

Vivian Zhi

where did you get the beige short sleeve collar shirt? 'tis a nice shirt (clearly asking all the important questions here, i know)

Sabrina Cruz

I'm pretty sure it's from Uniqlo lmao. - Sabrina

Sabrina Cruz

Honestly, this question might be a bit of a non-starter. A "purely objectively ethical AI" can't exist without everyone coming to agreement on what objectively ethical means - and the continuing existence of philosophy as a field of study suggests we're never getting that agreement. - Sabrina

Luis

When working on a video, how do you determine if/when to pivot and what to pivot to? I can imagine a lot of the time you don't know whether your hypothesis will work until well into the research process

Luis

Also off topic but really nice job in the graphics this episode! They were amazing

Sabrina Cruz

We split research into 2ish stages. The first stage is checking the idea for appetite, feasibility, and contingency. Would people be interested in this subject? Could we get a pretty good shot at an answer, even if we don't nail the landing? If we do fail, can we still provide viewers with something valuable? Asking these questions reduce the risk of scrapping video idea halfway through and also prep us for when things go wrong. In terms of what to pivot to if we do fail (which we so often do lmao), it really depends on the point of failure. It usually means we have a call and work together to figure out how we can still make the video valuable without starting from scratch. Despite what it sounds like, it's pretty easy because (usually) we just need to identify the point of failure and extract lessons from it. The motivation being that if that's where we failed, it might be where others might as well. So, if it isn't a lesson - at least it's a warning. - Sabrina

Luis

How did you first get introduced to ML? And are there any other areas of ML (like reinforcement learning, etc) you're interested in learning more about?

Luis

Also, my partner does RL, and at least from what she's told me it is very very hard. So you dodged a bullet by not going that route lol

Blaze Utz

Are you using a non-standard color palette in Jupyter? I wasn't sure because it was so quick on-screen. If so, what colors are you using?

Sabrina Cruz

I used Spyder and Google Colab in the video.

Sabrina Cruz

While in uni, I somehow ended up in a combo stats-ML class. It was very entry level but helped demystify the subject and gave me the confidence to try wacky applications. I'll probably play around with RL and GANs in the future but I'm tempted to go back to the basics to make something that actually works for once. - Sabrina

Richa Prasad

Question on how the scripting vs. shooting vs. re-scripting vs. editing vs. animation workflow happens? How much of the B-Roll and animations are decided before you even start? Curious about your workflow generally.