Thumbs up for maximizing meaning.

@martiddy

2 жыл бұрын

Other KZreadrs would worry only about the amount of views that they get in their videos. Károly is the only one I've seen that sacrifice views in order to give his audience a better understanding of certain topic in which he's not an expert. Respect!

@mkbettm9188

2 жыл бұрын

Mad respect

@Bat0541

2 жыл бұрын

Lets see Paul Allens Meaning.......

@bklanyon176

2 жыл бұрын

His credibility was greatly enhanced by acknowledging the extent of his present abilities.

@rhettmelton

2 жыл бұрын

"It's not about winning this particular game, it's about playing in such a way that you get invited to the maximum number of games." -Jordan Peterson (Maps if Meaning lecture "Story and Meta-Story")

Attaching these nice graphics to the environment is the best PR stunt in reinforcement learning Deep Mind did so far. I'm happy these graphics make RL more interesting to the general public. Thanks to you for enabling further dissemination!

@GabrieleNunnari

2 жыл бұрын

I was just thinking the same. A nice graphic does allow to understand what is happening and is also "pleasing" to the eye

@AICoffeeBreak

2 жыл бұрын

@@GabrieleNunnari I often wish all academic departments would have a team focusing on scientific infographics and helping their researchers with beautiful figures.

@justinwhite2725

2 жыл бұрын

If it wasn't for videos like this (and yours) hobbyist programmers like me wouldn't be interesting in trying AI projects.

@GabrieleNunnari

2 жыл бұрын

@@AICoffeeBreak I do also wish that academic departments would have a team working on that, but in research there is already the bare minimum amount of money to make research itself. A proper presentation would require another big investment, or a very talented researcher that is willing to take his work to the next level and spending his valuable time in learning how to do it.

@AICoffeeBreak

2 жыл бұрын

@@justinwhite2725 :blush:

"And you would think that the Starwars references would end here, no. Not even close, look(Luke)" That was smooth! 3:45

@mostlyokay

2 жыл бұрын

I thought he was about to point out the rotating agent, and say "Ah, let's try spinning - that's a good trick".

@unliving_ball_of_gas

2 жыл бұрын

4:00 "grabs his lightsaber, and takes the high ground"

"What a time to be alive!" could have a whole different meaning in the future when we are the hiders.

@mistaburrito

2 жыл бұрын

^^^^ This

@atlascove1810

2 жыл бұрын

I swear every robot uprising joke will be used against us.

@ultimaxkom8728

2 жыл бұрын

@@atlascove1810 _"Heh, as if such an absurd thing could happen."_ - Homo Sapient (evolutionary carbon lifeform) *No.[EXPUNGED],* Earth (former of New Terra)

@neils_xd4100

2 жыл бұрын

bump

@misovejasescuchanmivoz

2 жыл бұрын

The fall of the global economy will come first, global anarchy will be first.

5:58 AI already figured out the concept that you need to destroy other beings to defend yourself, this is earlier then expected.

@theopoldthegamer4284

2 жыл бұрын

Actually, it was taught that

@rantingrodent416

2 жыл бұрын

Not it didn't. To figure out the concept of destroying other beings to defend yourself, you would first need to understand what "beings" are, have a concept of self, and figure out destruction. This agent doesn't understand anything. Don't anthropomorphize an optimization algorithm.

@TheMenIdo

2 жыл бұрын

@@rantingrodent416 I'm not anthropomorphizing, he has to destroy the other agent to keep winning right, its purly optimising. a purly "optimising agent" advanced enough can be threat to humanity just because we are inconvinenant to its goals. Its expected but concerning that this behavior is already being seen in prototype AIs.

@aaronking2020

2 жыл бұрын

@@rantingrodent416 it kind of does understand it needs to defend itself, but at the same time it doesn't understand that it itself is a being, since it's just an AI with no sense of self.

@aaronking2020

2 жыл бұрын

@@bronzehd6212 bruh its not smart enough to do anything you just said lol

I'm just throwing an idea in the air. Do you think someone at DeepMind would be interested in helping with the video on their protein prediction tech?

@TheChristmasCreeper

2 жыл бұрын

That would be kind of cool. I don't think I've ever seen him invite guest speakers for topics he isn't confident in speaking about himself yet.

@teukurama3569

2 жыл бұрын

Great idea! I would love to see it

@edwardmitchell6581

2 жыл бұрын

With a million subs I think he can get who ever he wants for a 5-minute video.

Finally, true gamer AI. cant wait to see their steam libraries

@4GdaTim

Жыл бұрын

What a time to be a gamer!

@doggo2836

Жыл бұрын

@@4GdaTim 😂

Year 2030: 2 minute papers uploads are now 10-hour documentaries 👀

@101perspective

2 жыл бұрын

That are produced by AI.

@Naxt366

2 жыл бұрын

2030. No man alive

@sourdonkeyjuice

2 жыл бұрын

Yep, just give the AI a 2 minute video as a starting point and it extrapolates the rest.

@NetherHawk

2 жыл бұрын

@@Naxt366 Oh my god... Women took over the whole world?

@gogokowai

2 жыл бұрын

All that exists are AI bots that produce videos and farm views from other AI bots watching to generate their own relevant content

Have no idea whether to be excited or scared by these incredible advances!

@Bhodisatvas

2 жыл бұрын

Not long until AI makes all human decisions

@penguinista

2 жыл бұрын

Be both.

I remember that hide and seek!

@webx135

2 жыл бұрын

I love how they made them smile and laugh while playing. It's kinda adorable.

@mikeohc

2 жыл бұрын

@@webx135 Adorable until its your turn to hide

@lorrdy7640

2 жыл бұрын

Loved how they broke the engine at some point

Get the experts to guest in your videos. Maximum meaning! Thanks for the great videos.

Great respect for optimizing for meaning and teaching, instead of views. Props to you!

My hope for this eventually working in Super Mario 64 keeps going up.

@OnEiNsAnEmOtHeRfUcKa

2 жыл бұрын

I'm excited for when it learns to play card games.

@iwersonsch5131

2 жыл бұрын

@@OnEiNsAnEmOtHeRfUcKa eh, card games are a lot different controlling a character in 3d or even 2d space. You might be better off following chess and go AIs

@mmmmmmmmmmmmm

2 жыл бұрын

Make it rediscover all the A press saves from scratch and see how long it takes

Training artificial intelligence is definitely my favorite topic as of right now. Thank you for the awesome videos. love what you do.:)

I find the military potential of AI frightening, the human innovation of AI downright fascinating.

@jorgesaxon3781

2 жыл бұрын

I have no mouth and I must scream warned us about this

Interesting video, but I would've liked to know how these agents were trained

@devanmallory5304

2 жыл бұрын

Yea, I would be curious to know how many games they were shown

@PinataOblongata

2 жыл бұрын

@@devanmallory5304 They run through thousands of iterations.

@PinataOblongata

2 жыл бұрын

You give them simplistic, generalised functions like "maximise your points". The AI throws stuff at the wall until it notices something that increased points and then hones in on that, and repeats until optimisation has occurred.

@devanmallory5304

2 жыл бұрын

@@PinataOblongata is that the actual number, only a thousand? Normally I thought reinforcement algorithms take millions of games for complicated stuff like this

@Maxawa0851

2 жыл бұрын

@@devanmallory5304 depends on the thing, could be thousands or millions

Took a while for another video, glad youre back!

@foxxcvii7170

2 жыл бұрын

When you're a doctorate and your videos are top quality it makes sense life will delay these masterpieces of information.

Justs when i thought i couldn't like your channel anymore you admit your limitations in reference to covering alphafold, which I consider the height wisdom. Keep up the great work and thanks for the inspiration.

This is so cool! Thank you for sharing in such a clear and understandable manner :)

Reinforcement learning with very high number of iterations was one of those videos that made me want to study something in the field. I am happy in my 5th semester learning computational linguistics and had a great eye opener in a deep learning class today. Will continue to watch your videos to expand my horizon.

4:06 Don't do it Red Agent, Green Agent has the high ground!

Considering the tag video was my favorite video so far this is even better since it’s improved so much

Just the fact you essentially said ‘I want to talk about this, and it would get a lot of views, but I don’t feel I’m at the level of knowledge/understanding to give it a proper video yet so I’m gonna hold off’ is amazing and got my subscription. Keep up the great work!!!

Thanks for Maximizing Meaning! DeepMind is exploring the impossible and it's inspiring to see.

I keep finding myself holding on to my papers. I think even if I only had a passing interest in machine learning, I'd still be watching this channel. You've created a great portal into piquing interest and promoting learning in your field. It's a great time to be alive. And we'll see you - next time.

0:20 that was the video that made me sub to your channel.

These videos make my day!

We got an 8 minute paper today!

"These agents are not preparing for an exam, they are preparing for life" ... or dear, we are doomed :D

I love how you made a two minute long summary of another two minute paper.

Thanks... for making... this informative...video!

Phenomenal finding and equally spell binding narrator. Keep up the great work. Meaning will prevail.

Ahh... I really love these kinds of stuff. I hope more these kinds of game emerge and want to see their creativity!

I have a feeling that there's soon going to be an A.I. (through its process of elimination) that will finally be able to always generate many trillions of very beautiful unique images from learning what each of us love.

THANK YOU for everything you do!

Maximizing meaning. Thank you.

My favorite part of the OpenAI hide and seek experiment was when the seekers learned to exploit the physics engine by grabbing the box that they stand on, or sandwiching themselves between the wall and a ramp.

I was waiting for this, bless you.

Can't wait for this exact footage to make up the first five minutes of the next RL video!

Haven't seen interesting stuff around YT in a while, very nice

Subscribed for maximizing meaning.📈

I am so tired my eyes feel like they are about to fall out. But I need to watch this video before I sleep

I'll read the paper but I'd love a bit of information about how these AIs were trained and how the new problems were presented to them

Incredible work done by Deep mind thank you for sharing. It's incredibly humble that you are maximizing meaning not views.

The AI catch paper is already two years old?! How time flies!

can't believe its been 2 years since that open AI video.. its what got me into this channel lol

6:27 I love the enthusiasm

Awesome vid bro!

I have been waiting for a new video like this every day since the hide and seek paper. ! Thank you

This guy single handedly made me interested in this type of things. And I think I've seen this scene before in a video.

Deepmind's really putting out some magic recently. I can't wait to see what this kind of research means for game agents!

4:00 Takes the high ground while also spinning for a good trick, Uses both sides of the force this one does.

They teach this in Cognitive Science classes in Cognitive Psychology too; these are Agent-Based Simulations, they can be designed from multiple softwares, but this one's with a learning A.I. which strategizes between past knowledge, but also what the agents are pre-configured and how the maps can let them do or not. Example: the maze experiment is a basic one, where the programmed agent can move in all 4 directions, has limited field-of-view so when it hits a wall, it will either try another direction or backtrack and find another way.

I Love these Game Ai's I also made my own snake Ai Thanks for educating us :D

Amamazing video!!!!

So incredible the progress made. I can only imagine the potential this kind of AI would have within video games. It would make video games far more immersive and interesting.

Awesome as always!!

Love you man. You are a respectable person

I'VE BEEN WAITING FOR THIS

Maximizing meaning. God I love this channel

You can invite for an interview! And let the creators explain in a short amount of time, that would be a nice experiment for the channel!

I think it's worth pointing out that the main novelty of this work is a method to generate huge variety of unique worlds with "smooth" transitions between them. Each world is defined by 3 independently generated parts: environment, players, reward functions. This allows agents to be trained on a big variety of unique tasks and this is how trained agents succeed at 0-shot holdout set of manually crafted tasks (like hide and seek and capture the flag). In some sense 0-shot learning in XLand is similar to GPT-3.

Great video! I would love to hear your thoughts on some of the things revealed in Tesla's latest AI day. A lot of it goes over my head but when you get excited about something I know I should be too. I believe they even mentioned the Photorealism Enhancement paper you made a vid of a few weeks back. Do you have a platform where you may share such thoughts as its not exactly a paper?

@tauceti8341

2 жыл бұрын

Lex Fridman has made a video of some of the highlights from AI day, Sounds like you might find interest in it!

I wonder if this AI could work in a different modality, say, in language instead of 2d environment. It'd be a nice addition to some NLP neural net, like GPT-3, acting as some implementation of long-term planning.

sir you are great! thanks for the amazing video!

Great video, really fascinating what these generalized agents can do. ps. Friendly neighborhood Biochemist here if you want to ask any questions about proteins that you are struggling to understand happy to help

Very thoughtful of you to not speak about something you think you don't know enough about, too many people spread false information these days in an attempt to seem clever. It takes a wise man to admit ignorance.

Thanks for this awesome video, do you have the link to the protein structure prediction paper plz? :)

Good training for Terminators!

What a time to be alive!

Exactly.. what a time to be alive

1:55 the other guy is helping to bring one of the boxes closer for his buddy.

i have waited a long time for a follow up on the hide and seek video and this is great!

As a structural biologist, it makes me pleasantly happy that you are giving alphaFold and the protein solving problem its due diligence! We've already started using AlphaFold in our lab to start asking some tricky questions that we had only small amounts of experimental data on. AlphaFold is certainly not perfect but boy is it impressive!

Remember making sense is also mental. So working together is one single sense where every atom in the Universe is a sense.

And I thought that Hungary had nothing going for it in the youtube scene, but here I am watching this video!

Kudos for knowing when there is a topic that you are not ready to cover yet. It is an admirable ability which appears to be in short supply on the interwebs. People who can't recognize that about themselves clog up the airwaves and make it harder to find the knowledgable folks.

As a minecraft parkourist, (someone who plays parkour in minecraft alot) I wonder if this ai can find ways to do jumps in minecraft with set distance to gain momentum, and distance to end goal. We've never been able to do a 5 block jump using flat momentum (like only a floor, and nothing else) and have proven it using bare force and math, untill recently when we found a common mod called optifine had an exploitable speed miscalculation (on some old versions of it) which can give a speed boost by turning over 900million degrees, resulting in an about 1.03% speed increase, making a 5 block jump possible on flat ground.

@ezravandermeer6192

2 жыл бұрын

that'd be cool

@alengm

2 жыл бұрын

General rl ai vs baritone bot

@Grocel512

2 жыл бұрын

900 million degrees quick scope

@gwentarinokripperinolkjdsf683

2 жыл бұрын

What are you smoking. You can totally do a 5 block jump, that's the furthest you can do though. And optifine is client side only. Wtf

@LightslicerGP

2 жыл бұрын

@@Grocel512 it makes a weird calculation and just breaks it, giving more speed than usual lol

"It's not about winning this particular game, it's about playing in such a way that you get invited to the maximum number of games." -Jordan Peterson (Maps if Meaning lecture "Story and Meta-Story")

@timonix2

2 жыл бұрын

Oh god. Every game is democracy

Maximizing meaning? You just maximized my heart with that line man

What humble comments at the end of the video. (I believe you could do the AlphaFold ! ^^)

TMP: "look... Boom" Blue agent: *Disintegrates*

YAY YOU MADE A VIDEO ON THIS ONE 🥳🥳🥳

amazing! made my day

1:17 I was thinking the blue ones could use the ramp to jump out of the whole level

That's amazing! :O

really amazing!

The fact that the AI in King of the Hill has learnt to master eliminating its opponents could escalate in real life! AI has no intent to harm, but if it is given a goal, then it will probably find ways to beat humans in the real world!

@eyeofhorus1301

2 жыл бұрын

+Suraj Kothari No intent to harm? Opposing countries militaries and people with nefarious motives... hello?!

@danielyuan9862

2 жыл бұрын

@@eyeofhorus1301 "AI has no intent to harm" means an AI does not naturally have an intent to harm anyone. It has nothing to do with people.

@eyeofhorus1301

2 жыл бұрын

@@danielyuan9862 Since it has no intent itself its intent is dictated by the people who use it you're only half right

@eyeofhorus1301

2 жыл бұрын

@@danielyuan9862 Also it could literally be designed to have intent to harm so thats not necessarily true either. It can be anything you tell the computer to be...

5:54 I see red is doing a victory dance

All hugs and puppies until the AI realizes that “stop the ball from touching the red floor” is best achieved by destroying either.

Yes, like other comments said: thanks for maximizing meaning

Amazing!!!

AHH was waiting for part 2 of these nutty AI gamers. Love the content

It is amazing to think, for millions of iterations in evolution. Like the AI that runs around aimlessly for millions of games, millions of generations of creatures have died due again and again to be able to benefit the entire species through gene selection.

@roadblok6713

2 жыл бұрын

We are exactly the same except our environment is more complex and we experience time differently.

The AI bending the rules to get closer to the pyramid is a perfect example of how asking AI to “end human suffering” will result in ending human existence 😅

@crazybunnyproductions7287

2 жыл бұрын

I recommend Bad Writing Advice's video on evil AI

ai is so incredible makes me excited for what is possible

What the time to be alive!! Said Skynet before getting read of mankind...

Can you do summary of last few years of progress of AI and near future goals and regroup of more specific games achieved by ai deepmind atari, chess etc..

Awesome

I started beliving in AI with alpha go. If you play a bit of go you realize how amazing it is.