How to Keep Improving When You're Better Than Any Teacher - Iterated Distillation and Amplification

[@qwertymann1]

Without knowing the amount of time spent on the animations, I'd say it was totally worth it!

[@luksablp]

I think it really helped understanding the concepts

[@thefakepie1126]

what if it was 29 years and 3 months ?

[@climagabriel131]

@@thefakepie1126 lol, this a reference to his age?))

[@thefakepie1126]

@@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

[@climagabriel131]

@@thefakepie1126 oh, alright)

[@mattstuart-white450]

"How to keep learning when you're better than any teacher" - Rob, you have really let the positive youtube comments go to your head... 🤔

[@Gooberpatrol66]

Miles really wants to contain AI superintelligence because he doesn't want competition.

[@JohnJones1987]

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.

[@nephildevil]

🤣🤣

[@travcollier]

"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.

[@monad_tcp]

I'm an AGI, it helped me.

[@travcollier]

@@monad_tcp I welcome our new robot overloads.

[@MrBleulauneable]

Alright I'll watch it twice then ! (The animations are neat btw !)

[@qzbnyv]

Makes sense after seeing the Grant Sanderson credit for the animation code :) 3b;1b

[@alekseysoldatenkov5675]

NWN Oh shit! Keep the dope collabs going.

[@rogerab1792]

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...

[@YourMJK]

Yeah, you do notice it uses 3b1b's "Manim" Framework

[@MrBleulauneable]

@@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).

[@shamsartem]

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

[@joshuacoppersmith]

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.

[@KivySchool]

Excellent! High quality animations with high quality teacher. I'm so grateful for all the good content you have been posting here.

[@ministerc9513]

Roberts ability to clearly explain complicated things is itself an art form.

[@DeliciousNubbs]

Holy hell, this was awesome and very clear!

[@ze4017]

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

[@Jmoneysmoothboy]

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

[@mattf2219]

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 :)

[@RyanTosh]

The only dislikes are from AGIs who know we're onto them...

[@REOsama]

This is pure gold, not only is it informative, but is explained in an excellent way

[@NickCybert]

The animations actually really helped make your explanation clear.

[@pafnutiytheartist]

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.

[@matthewhubka6350]

Distillation requires a lot of resources to get the good results. For 1 vid he’s better off just amplifying

[@Ruptured_AU]

Animations arw SO worth it thanks a lot.

[@spirit123459]

Great animations and explanation!

[@thrallion]

legit my favourite channel on youtube by far

[@SJNaka101]

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

[@thrallion]

@@SJNaka101 hey thanks, good guesses as i already watch all those except what I learned :) will look into it

[@NeonStorm5]

Probably the most intuitively informative video I've ever seen.

[@friiq0]

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!

[@moneypowertron]

Fantastically intuitive explanation, Robert. The animations were a crucial tool. Thank you for the efforts!

The quality of your videos have really improved. This was very well animated and explained. Thank you, please keep them coming.

[@polares8187]

This was superb. Fantastic animations. Clear explanations. Awesome all around.

[@reidwallace4258]

This is giving me flash backs to the dune novels. Paul was just doing treesearch all along.

[@lewisleslie2821]

Reid Wallace i read dune for the first time last month, that’s a great comparison

[@solemnwaltz]

The animations are great! I took mental notes specifically on how satisfying and descriptive they are. Well worth the time, in my opinion. c:

[@willd4686]

Animations were very helpful. I'm not sure how much work they were but I'm grateful that you did them.

[@Anymodal]

Dear Rob. Ive learned so much from your videos. Top quality education

[@chriscanal999]

Great video! I’m consistently impressed with how wonderfully distilled the information on your channel is. Thanks for all the hard work and interpretability :)

[@HereWasDede]

Those animations were AWESOME!! Thanks

[@Celastrous]

Wow this was amazing. I loved the animations. The explanations were so clear

[@GglSux]

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.

[@keithklassen5320]

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.

[@gloverelaxis]

Animations were worth it. They help immensely

[@peto348]

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.

[@snfn7847]

Good to see you're still alive

[@stasisthebest]

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.

[@JohnnyDoeDoeDoe]

Your absolute best video yet!

[@kanva4]

This is underrated

[@aronchai]

I've seen this concept floating around a lot, but didn't really understand it 'til now. Thanks!

[@vshalts]

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!

[@mare4602]

im so happy you are back, high quality content as always.

[@SHAD0W99V0RTEX]

To be honest, I expected a self-help video about autodidacts but I was pleasantly surprised anyways. Good stuff! This is very ingenious.

[@hacker6284]

Those animations were totally worth it! Really well done video

[@Gloubichou]

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

[@roberttomsiii3728]

Thank you for being MY amplified agent.

[@kennynicoll6277]

This nicely mirrors Kahneman's description of system 1 and 2 in human decision making.

[@danielcallegaribr]

Kenny Nicoll hey, this is a great insight!

[@BuceGar]

Great video and explanation, doesn't address the fundamental problems we will invariably have with AGI, but shows some of the potential dangers.

[@briansmithbeta]

The animations really helped me understand some things that had been confusing for me! Thanks!

[@lacielaplante5702]

Your explanation is absolutely outstanding.

[@reverse_engineered]

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.

[@amargasaurus5337]

Those animations are great! Be proud ♥

[@ArtinKavousi]

you are wonderful Being! for what you doing ! so helpful in these time and age of probabilities!

[@ADAMBLVCK]

This channel is gold, and so is the work you're putting in! Simply great!

[@brunosonza787]

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!

[@kensmith5694]

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.

[@Raymaniak]

Your videos are approachable and fascinating. Keep up the good work, Rob! You're awesome.

[@szymonbaranowski8184]

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...

[@jessty5179]

Thank you for sharing Rob !

[@8989youu]

Wow, very clear and to the point. I love it. Definetly worth sharing 😁

[@Cabothedog14]

I've been waiting for a new video!! Glad to see you're uploading again :)

[@hosmanadam]

Your videos are perfectly optimized to be easily processed by my learning function.

[@nielsgroeneveld8]

Few lectures have been as unbelievably good as this one.

[@briancox3922]

Wow, you really are good at explaining these subjects. Thank you.

[@Viniter]

Those animations are really cool!

[@Sharklops]

This was fantastic! Very well done. Cheers!

[@xystem4701]

And here I was thinking this was just going to be a simple minimax video!

[@randommm-light]

Very nice and understandable. Thx. The limits of architecture in n-dimensions..

[@TheNeilChatelain]

Production value has definitely improved considerably

[@StevenAkinyemi]

Can't wait for the next video! I'm not sure alignment can be maintained the more complex an agent becomes. There will always be abstraction difference between what we want it do and what it does to optimize itself. This means we have to always tune the alignment as the agent becomes more complex. There is perhaps a point where the agent's comprehension of the universe explodes beyond our grasp and we won't be able to align it at that point. In fact, we might have to restrict it's optimization process when we discover its intelligence is getting beyond our control. These are just theories in my head.

[@JohnDlugosz]

I wonder if that's the principle behind what I heard about training a small model (fits on a PC) with the major LLMs (e.g. GTP-4) and it only took $600 in running costs to make the small model act very much like the big one.

[@GuuraHeavenbound]

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

[@PflanzenChirurg]

Best KZbin Video of the Month

[@sky5d]

the animations really paid off.

[@Koffeinsuechtigi]

Thank you for your well crafted explanation!

[@DeclanMBrennan]

Crystal clear explanation with no waffle. Thank you. The graphics are so useful, they need their own name. How about didactic visualizations? :-)

[@serenityindeed]

Your animations were really good! Enjoyed the explanation as well.

[@rogerab1792]

Really well explained, thanks!

[@CyberAnalyzer]

Wow, fantastic animations! The content is so deep! I love it!

[@jeanmichelsarr6040]

Great idea, concise, precise.

[@wassollderscheiss33]

If the amplification process leads to a system that solves a problem optimally that implies there to be an optimal solution. 1. An optimal solution for chess is a table of optimal moves given every possible board. Given the introductory premise, that would mean a system with the size of an optimally compressed version of that table could play chess optimally after infinite iterations of training. 2. However, an optimal solution to chess can be represented more efficiently than with the mentioned table (so I think). Maybe through some math or just by leaving out positions of the table that can never be reached using the table. Does that mean, the amplification process will produce an optimal chess solution even in a system with the size of the optimally compressed version of that reduced table?

[@5ty717]

Brilliantly explained

[@ulissemini5492]

awesome! this makes so much sense! this is exactly how i get better at chess, play a game quickly, then go back and calculate a lot to find the better moves, then improve my intuition! its so awesome that you said it in such a way that now i feel like i can write a program to become superhuman at anything :D

[@dylancope]

The animations were great! Very intuitive video :)

[@YouAreLoved321]

rob miles new video boys get the popcorn!

[@Signonthisline]

I don't bookmark videos very often. GJ. also I subscribed (more common)

[@lobrundell4264]

Ugh so worth the wait!

[@dylancope]

How did I miss this?! I can't believe I hadn't "hit the bell" on this channel yet.

[@Gorabora]

Awesome video and very easy to understand, keep up the good work !

[@jonathanquarles3708]

You explained this so clearly, thank you!

[@DamianReloaded]

Worth watching a few times! ^_^

[@ivanshmarov2866]

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.

[@justdiegplus]

Most important video on AI on the internet.

[@oguretsagressive]

Wow! An awesomely good explanation of how AlphaGo works!

[@jameslincs]

This video deserves more views

[@RagingPanic]

How can we know for certain that alignment is transitive? If an AGI is made to uphold and strive for certain principles like health, well-being, safety, risk-aversion, transparency, etc, how can we know that it will not take it's interpretation of one or more of those 'principles' to the extreme? An AGI concerned with the safety of a certain task might deem the task too dangerous to be done at all, but as people we know that task must be done. Even if we have an AGI aligned with us to start with, I'm not convinced that once it starts optimizing the things (both humans and the AGI care about) it will perfectly inherit and preserve its ideal alignment all the way through. Great video as usual, keep it up!

[@DavidHimmelstrup]

Love the animations. Did you use manim?

[@RobertMilesAI]

Yep :)

[@DavidHimmelstrup]

@@RobertMilesAI Is your code open-source? I would love to have a look.

[@RobertMilesAI]

@@DavidHimmelstrup No, this is code I wrote with no intention of publishing, only needing it to run correctly once. It is a spaghetti hell nightmare.

[@DavidHimmelstrup]

@@RobertMilesAI Oh don't be shy. Please throw some spaghetti hell nightmare my way: [e-mail]

[@ardweaden]

Absolutely brilliant explanation!

[@biquinary]

Is that Go by Public Service Broadcasting in the background at the end?

[@RobertMilesAI]

That's the name of the game! :p

[@GoatzAreEpic]

Absolutely amazing and helpful for learning strategies as well( learning to become a front end dev atm)

[@Hexanitrobenzene]

Yay ! We missed you, Rob :)

[@foobargorch]

if the distillation process is lossy, doesn't that imply that you might not reach a fixpoint, but actually degrade eventually, since you are potentially amplifying that error?