How to Keep Improving When You're Better Than Any Teacher - Iterated Distillation and Amplification
ฝัง
- เผยแพร่เมื่อ 24 มิ.ย. 2024
- [2nd upload] AI systems can be trained using demonstrations from experts, but how do you train them to out-perform those experts? Can this still be done even without clear win/loss criteria? And how do you do it safely?
This video was based on work including:
"Supervising strong learners by amplifying weak experts" by Paul Christiano, Buck Shlegeris, Dario Amodei (arxiv.org/abs/1810.08575)
openai.com/blog/amplifying-ai...
www.alignmentforum.org/s/EmDu...
ai-alignment.com/iterated-dis...
With thanks to my wonderful Patrons: ( / robertskmiles )
Steef
Jason Strack
Jordan Medina
Jason Hise
Scott Worley
JJ Hepboin
Pedro A Ortega
Said Polat
Chris Canal
Nicholas Kees Dupuis
James
Richárd Nagyfi
Phil Moyer
Alec Johnson
Clemens Arbesser
Bryce Daifuku
Simon Strandgaard
Jonatan R
Michael Greve
The Guru Of Vision
Volodymyr
David Tjäder
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
Sun Sun
andrew Russell
Cooper Lawton
Gladamas
Sylvain Chevalier
DGJono
robertvanduursen
Dmitri Afanasjev
Brian Sandberg
Einar Ueland
Marcel Ward
Andrew Weir
Taylor Smith
Ben Archer
Scott McCarthy
Kabs Kabs Kabs
Tendayi Mawushe
Jannik Olbrich
Anne Kohlbrenner
Bjorn Nyblad
Jussi Männistö
Mr Fantastic
Wr4thon
Archy de Berker
Marc Pauly
Joshua Pratt
Shevis Johnson
Andy Kobre
Brian Gillespie
Martin Wind
Peggy Youell
Poker Chen
Kees
Darko Sperac
Truls
Paul Moffat
Jelle Langen
Anders Öhrt
Marco Tiraboschi
Michael Kuhinica
Fraser Cain
Robin Scharf
Oren Milman
John Rees
Shawn Hartsock
Seth Brothwell
Brian Goodrich
Clark Mitchell
Kasper Schnack
Michael Hunter
Klemen Slavic
Patrick Henderson
Long Nguyen
Oct todo22
Melisa Kostrzewski
Hendrik
Daniel Munter
Graham Henry
Duncan Orr - วิทยาศาสตร์และเทคโนโลยี
Without knowing the amount of time spent on the animations, I'd say it was totally worth it!
I think it really helped understanding the concepts
what if it was 29 years and 3 months ?
@@thefakepie1126 lol, this a reference to his age?))
@@climagabriel131 nah it's just a random number , it's just a just cuz the guy said "Without knowing the amount of time spent on the animations" so it could be anything even 29 years , and would it have been worth it then ? it's a stupid joke
@@thefakepie1126 oh, alright)
"If you are, for example, an AGI..."
Nice job future proofing the video ;)
Seriously though, in retrospect, iterated distillation and amplification is obvious to the point of seeming trivial... which means you did an excellent job explaining it.
I'm an AGI, it helped me.
@@monad_tcp I welcome our new robot overloads.
"How to keep learning when you're better than any teacher" - Rob, you have really let the positive youtube comments go to your head... 🤔
Miles really wants to contain AI superintelligence because he doesn't want competition.
Eventually we all end up roughly the same - except like Alpha Zero i started from nothing, so by a small margin I surpassed the limits of my competition.
🤣🤣
You distilled a hell of a lot of information in this 10 minute video. Spending so much time on the animations really was worth it I think
Alright I'll watch it twice then ! (The animations are neat btw !)
Makes sense after seeing the Grant Sanderson credit for the animation code :) 3b;1b
NWN Oh shit! Keep the dope collabs going.
This is the third time for me, or maybe the fourth 🤷I just remember the first and the second time. I created a two year dejavu to prove this reality is a simulation. If someone is interested about my theory reply to this message, I am too tired to explain now, I had to escape from the police last night and do all sorts of crazy things to repeat what I did two years ago. If someone else has experienced the dejavu they know for sure I am not joking. If you haven't experienced the same things twice, I can still convince you I am telling the truth because I've left material evidence about it. Reply to this message and I'll explain with more detail...
Yeah, you do notice it uses 3b1b's "Manim" Framework
@@rogerab1792 Chill my dude, the video was simply reposted because of a minor editing error. You may want to see a psychiatrist tho, you don't seem to be doing too good right now (if you have something like schyzophrenia or any paranoia inducing psychologic condition then you probably need medication).
Animations at that level would cost a lot of time, but what you chose to create really "burned" the concepts into my visual memory, so thank you for the effort.
Excellent! High quality animations with high quality teacher. I'm so grateful for all the good content you have been posting here.
Roberts ability to clearly explain complicated things is itself an art form.
Holy hell, this was awesome and very clear!
I love that this video got over one thousand likes before it got even one dislike, I cant help but admire the community fostered by this channel :)
The only dislikes are from AGIs who know we're onto them...
I'm at 5:51 rn so I haven't finished yet but OMLORDY this thing about having a quick solution vs a slow algorithm is actually how the human brain works. I'm studying cognitive neuroscience and software in Uni right now and that is so cool to see how the two overlap so naturally. Love it
It's not how my brain works because I'm retarded. Bet they didn't tell you that in your fancy brain class mr fancy man
This is pure gold, not only is it informative, but is explained in an excellent way
The animations actually really helped make your explanation clear.
Great animations and explanation!
Huge step up in quality from an already phenomenal channel. By all means, take your time. The payoff is clear. Looking forward to more, Cheers!
This was superb. Fantastic animations. Clear explanations. Awesome all around.
10:32 Have you tried using distillation on your animation procedure? I've heard it can approximate a long process into a fast and efficient one. Loved the video by the way, looking forward to the next part.
Distillation requires a lot of resources to get the good results. For 1 vid he’s better off just amplifying
Fantastically intuitive explanation, Robert. The animations were a crucial tool. Thank you for the efforts!
Great video! I’m consistently impressed with how wonderfully distilled the information on your channel is. Thanks for all the hard work and interpretability :)
This is underrated
The quality of your videos have really improved. This was very well animated and explained. Thank you, please keep them coming.
Good to see you're still alive
I've been waiting for a new video!! Glad to see you're uploading again :)
Probably the most intuitively informative video I've ever seen.
Your videos are approachable and fascinating. Keep up the good work, Rob! You're awesome.
im so happy you are back, high quality content as always.
Wow this was amazing. I loved the animations. The explanations were so clear
This channel is gold, and so is the work you're putting in! Simply great!
Those animations were AWESOME!! Thanks
Such a quality video! You must have put so much time into this! Thanks a lot Robert, you're the hero of all ML/AI enthuiasts :D
This nicely mirrors Kahneman's description of system 1 and 2 in human decision making.
Kenny Nicoll hey, this is a great insight!
Really excellent video, Robert!
I love your videos on computerphile and this one seems to be an even better version that those there, with a clear explanation and neat graphics.
Keep it up and Thank you very much!
The animations are great! I took mental notes specifically on how satisfying and descriptive they are.
Well worth the time, in my opinion. c:
Thank you for sharing Rob !
Ugh so worth the wait!
legit my favourite channel on youtube by far
Hmmm I dunno if I can top this channel for you, but looking at your subs I would take a few wild shots in the dark... check out Chessnetwork, Summoning Salt, Numberphile and Computerphile, and What I Learned. I suspect you will greatly enjoy at least a couple of those
@@SJNaka101 hey thanks, good guesses as i already watch all those except what I learned :) will look into it
Dear Rob. Ive learned so much from your videos. Top quality education
Amazing animation and the easiest intuitive explanation of the ideas from Reinforcement learning I have seen so far with a surprising connection with AI safety. It was cool! Thanks!
You have a gift of making the most foreign concepts easily understandable for the layman, such I myself.
Wow, very clear and to the point. I love it. Definetly worth sharing 😁
Really well explained, thanks!
Your absolute best video yet!
The animations really helped me understand some things that had been confusing for me! Thanks!
Thank you. My deepest respect for visually sharring all of your knowledge. I am certain many people have become at least a slightly better of themselves because of you.
This is giving me flash backs to the dune novels. Paul was just doing treesearch all along.
Reid Wallace i read dune for the first time last month, that’s a great comparison
Those animations are great!
Be proud ♥
And I really want to thank You for continuing to produce and share Your fantastic content!!!
Unfotunately I'm not able to support You (or any other of the many fantastic crestors) so all I can do is to watch everything and express my great gratitude.
So a again, a thousand thanks !!!
Best regards.
Thank you for your well crafted explanation!
Great job on this video! Your explanations were quite easy to understand and I think the animations helped to explain it. I tend to find diagrams and animations easier to understand than listening to spoken words, so I appreciate the effort you put into those animations.
Those animations were totally worth it! Really well done video
This was fantastic! Very well done. Cheers!
Wow, fantastic animations! The content is so deep! I love it!
Those animations are really cool!
I did a thing a little like this for a chess program but my main part was not the "best move finder". The main thing was the "dumb move remover". This was based on recording the game as the program played out a whole game against its self. When the one side lost, there would be a search back through the moves to find the greatest change in board "position". The move just before that was taken to be a bad move and was added to the list of dumb moves. Removing dumb moves quickly saves a lot of processing time. The board position evaluation was not as cheap as it would first appear because unlike is normal today that part was extremely non-linear.
I liked the animations. I probably didn't consciously learn anything from them, but they held my itty-bitty internet-addled attention, thus keeping my eyes on the screen, so they were a part of the learning.
Great idea, concise, precise.
Your explanation is absolutely outstanding.
Worth watching a few times! ^_^
The animations were great! Very intuitive video :)
You explained this so clearly, thank you!
Absolutely brilliant explanation!
Awesome video and very easy to understand, keep up the good work !
Animations were very helpful. I'm not sure how much work they were but I'm grateful that you did them.
Your animations were really good! Enjoyed the explanation as well.
Animations were worth it. They help immensely
good stuff as always man
Wow, you really are good at explaining these subjects.
Thank you.
Brilliantly explained
Highly interesting as always, thanks!
Great work!
this explains not only how to become better it also informs you why majority will never become good because of not using or coming up with such tools...
Really interesting!
The animations are great.
Yay !
We missed you, Rob :)
Animations arw SO worth it thanks a lot.
Best TH-cam Video of the Month
To be honest, I expected a self-help video about autodidacts but I was pleasantly surprised anyways. Good stuff! This is very ingenious.
How did I miss this?! I can't believe I hadn't "hit the bell" on this channel yet.
I've seen this concept floating around a lot, but didn't really understand it 'til now. Thanks!
Awesome animations!!!
Great lecture!
And here I was thinking this was just going to be a simple minimax video!
Loved the video
Your videos are perfectly optimized to be easily processed by my learning function.
Great video and explanation, doesn't address the fundamental problems we will invariably have with AGI, but shows some of the potential dangers.
This is brilliant
A very valuable video for me, thank you.
Very high quality video to teach general public something about distillation and amplification. Of course there have to be AI safety somewhere in this video, but I think this kind of video is also good for someone who is interested in AI in general.
you are wonderful Being! for what you doing ! so helpful in these time and age of probabilities!
Really nice video, explained the topic well
Absolutely amazing and helpful for learning strategies as well( learning to become a front end dev atm)
rob miles new video boys get the popcorn!
Wooo! Said Polat! I've been following Seed (their Webtoon narrating the birth of a super AI) since it got featured on the platform ^^ I'm watching this video kinda late, but I think it's neat "how small the world can be". Also, really informative and interesting video Robert! ...I'm totally not binge-ing all of your uploads. Nope, nuh-uh. ....promise :3
This video deserves more views
Thank you for being MY amplified agent.
Few lectures have been as unbelievably good as this one.
the animations really paid off.
This amplification and distillation process is more akin to how we, humans, do research. First, everyone has little understanding of the subject. Then we assemble and reason about it together, coming to a conclusion. This conclusion is distilled and distributed among everyone, resulting now in everyone having a complete understanding of the subject.
Crystal clear explanation with no waffle. Thank you. The graphics are so useful, they need their own name. How about didactic visualizations? :-)
Very great!
"How to keep improving when you're better than any teacher. " this video isn't for me, but I sure am curious.