AI Learns to play the Worlds Hardest Game

Поділитися
Вставка
  • Опубліковано 18 гру 2024

КОМЕНТАРІ • 7 тис.

  • @CodeBullet
    @CodeBullet  6 років тому +3236

    Hey Guys
    Its not more levels but it is the next best thing
    code-bullet.github.io/WorldsHardestGameAI/WHG/

  • @CodeBullet
    @CodeBullet  6 років тому +6410

    Holy shit, settle down guys I get it. I’ll do more levels.

    • @theboywholearned872
      @theboywholearned872 6 років тому +46

      Yay!

    • @lucasguia6030
      @lucasguia6030 6 років тому +58

      Code Bullet lol my first comment on UA-cam in a billion years.... make them learn at least the last level

    • @lilysowden4035
      @lilysowden4035 6 років тому +66

      Code Bullet If you're just making it evolve to find a certain set of directions to complete the level will the second level not be like starting completely from scratch? Could you perhaps try to make an AI that can solve multiple different levels?

    • @1menatbpe
      @1menatbpe 6 років тому +6

      Also if possible try to make it as efficient as your minesweeper AI.

    • @rudyerickson3830
      @rudyerickson3830 6 років тому +4

      I have no clue if this would work, but the ai with "free will" to run around without just random movements, ah who am I kidding he probably already tried or know it wouldn't work.

  • @wraein
    @wraein 5 років тому +866

    “Most players have figured out how to get out of the starting area”
    *Me, being fully represented by the cubes still ramming into the walls:*

  • @rustynail4109
    @rustynail4109 5 років тому +4903

    You should create AI to play Geometry dash

    • @jochen4207
      @jochen4207 5 років тому +75

      Hell yeah he should

    • @KingLaZrButBad
      @KingLaZrButBad 5 років тому +35

      GENIUS

    • @gdzefferokami5673
      @gdzefferokami5673 5 років тому +113

      An AI that could beat zodiac XD

    • @lphoc
      @lphoc 5 років тому +39

      no it's to easy, cause each level is the same and you just have to tap

    • @uvi_music
      @uvi_music 5 років тому +61

      Léo think again, it gets a lot harder than just that, I have been playing for 3 years and I got quite good so I would know

  • @squishmellow3
    @squishmellow3 5 років тому +1000

    Did-
    DID YOU PLAY THE WORLDS HARDEST GAME ON *_SCRATCH?_*

    • @carmihd
      @carmihd 5 років тому +6

      IKR

    • @carmihd
      @carmihd 5 років тому +19

      Also I

    • @fishy__2
      @fishy__2 5 років тому +5

      Squishmellow 3 YEA I WAS ABOUT TO SAY THAT XD

    • @fishy__2
      @fishy__2 5 років тому +3

      M3m3 Qu33n yea me too

    • @kaziahscats
      @kaziahscats 5 років тому +2

      I thinks

  • @sstream17
    @sstream17 6 років тому +5013

    Adding the incremental learning was a neat trick to get around the players stuck in the start. Overall very neat but I agree with others, I'd like to see a video where the AI learns the rules of the game, not the path of a particular level. This would be more fun to watch with more levels going forward.

    • @FortySixandTwo595
      @FortySixandTwo595 6 років тому +64

      If there's some open source visual AI and you could perhaps direct it to anaylze why it died visually, or easier perhaps tell it blue dots = bad alongside death = bad and high distance to exit upon death = bad I think it could be possible. But frankly I know jack shit about AI coding.

    • @john_hunter_
      @john_hunter_ 6 років тому +39

      Forty Six and Two, machine learning could work. You can feed it information about where it is on the screen and the position of the dots, and then it will produce an output for what direction to move. It could probably even use convolutional neural networks where it looks at an image of the game and figures all that stuff out by itself.
      There are some open source machine learning libraries as well. I think tensorflow is a popular one.

    • @pierrecurie
      @pierrecurie 6 років тому +35

      AI can already play chess, go, mario, and old atari games. Obviously, we don't expect a 7min video to teach us all the intricacies of AlphaGo, but generalizing the AI to be able to handle rules (and figure out a way to win) would be awesome.

    • @ceigey-au
      @ceigey-au 6 років тому +20

      John Hunter just to clarify, what’s happening in this video is also machine learning - it sounds like what you’re describing is neural networks (of which the confusingly named deep learning normally falls into but also many other interesting approaches), which tend to use networks of simulated neurons as opposed to evolutionary algorithms like this one.
      The two are combinable too - you can have evolutionary neural networks with back propagation (one might argue that’s what the human brain is an example of).

    • @sstream17
      @sstream17 6 років тому +7

      Camper Josh what why?

  • @cionm
    @cionm 6 років тому +4078

    All you have to code is
    If “redRectangle” touch “blueCircle”
    Then {don’t}

    • @yetyetyeyet6788
      @yetyetyeyet6788 6 років тому +244

      Lmaooo

    • @JabroniBomb
      @JabroniBomb 6 років тому +51

      Gerbbzz actually we see at the begining of the video that this game was a made on a website called scratch ( which is what i use to make allnof my games) and on scratch there are no lines of code but rather blocks. so no you dont.

    • @tankkong4749
      @tankkong4749 6 років тому +32

      thats not AI tho, your saying to artificially input commands...., however, in this case the system registers errors and learns from them..essentially getting better each time which is like the human brain....

    • @soulyfr
      @soulyfr 6 років тому +4

      Just telling you that it was an example he used. He CAN actually code and he does. In his Stevie the dinosaur video you can see him coding!

    • @JabroniBomb
      @JabroniBomb 6 років тому

      Attila Vinklmann ok whatevr

  • @sergiolikesdonuts
    @sergiolikesdonuts 6 років тому +2312

    I WANNA SEE ALL LEVELS!!

    • @thegt1647
      @thegt1647 6 років тому

      Sergio Franco truuuuuuuuuu

    • @Kevinofrepublic
      @Kevinofrepublic 6 років тому +60

      The problem with doing all levels is that the AI doesnt learn to play the game. The AI that can beat the first level cannot beat the second because its not designed for the second. You would have the take the program and essentially start over the incremental learning for each level.

    • @fierypilot2195
      @fierypilot2195 6 років тому +11

      Kevinofrepublic who cares!!

    • @arcen4426
      @arcen4426 6 років тому +23

      The point is for the AI to learn, hence the name of the video 'AI LEARNS to play the World's hardest game'. It would also take a lot of time and effort to create every single section.

    • @therealstarMoses
      @therealstarMoses 6 років тому +1

      Yaaas

  • @Septimus_ii
    @Septimus_ii 4 роки тому +610

    I feel like they haven't really learnt the rules of the game, they've just learnt to follow that exact path

    • @IAmTjay116
      @IAmTjay116 4 роки тому +73

      They learned the exact path to victory

    • @nebulastar2130
      @nebulastar2130 3 роки тому +111

      The AI simply "thinks": "ok, If I go up I die, but if I go right I survive as I saw in the past generations. What now?"
      It tries a move and adds the result (move and its consequences) for the next gen

    • @okay2037
      @okay2037 3 роки тому +60

      I think that's where humans surpass AI in the fact that we know how to learn, how to critically think and extrapolate concepts outside of ourselves to other things and learn from that type of thinking, while a basic AI only knows how to observe and induct information to make a path to victory without observing the major implications of what they're doing. I think a more advanced AI could learn to see outside of itself though.

    • @suomusintti
      @suomusintti 3 роки тому +6

      @@okay2037 Yeah and more advanced AI could avoid the dots and move away when they are going to hit

    • @greebmcfleeb5554
      @greebmcfleeb5554 3 роки тому +12

      ​@@suomusintti i feel like you could give the ai the ability to "see" the dots and know their positions. the only problem might be that if you give it that information, a program doesn't have the delayed reaction time and imperfect judgement of a human so it might be too easy once it learns the rules. Idk how ai works really but I feel like this is super simplified

  • @asdrubalegirolamo660
    @asdrubalegirolamo660 6 років тому +176

    When you can't beat a level so you recreate the whole level and add AI to beat it for you. Nailed it.

  • @cuckoo_head
    @cuckoo_head 6 років тому +1971

    please make more levels! turn this into a series already!
    edit 8 hours later: holy shit this got 1k likes? you guys are crazy.

    • @beaverstever1083
      @beaverstever1083 6 років тому +10

      DO IT

    • @c2h6
      @c2h6 6 років тому +3

      cuckoo head that would be great

    • @mastrae8510
      @mastrae8510 6 років тому +3

      Yasss

    • @mwperk02
      @mwperk02 6 років тому +2

      Needs all da levels plz also isn't there a second game in the series?

    • @QuestionMarkOHai
      @QuestionMarkOHai 6 років тому +3

      Agreed

  • @venkyratnam
    @venkyratnam 6 років тому +1285

    AI learns to code and develop more AI.

  • @spiderking8011
    @spiderking8011 4 роки тому +280

    Code bullet: can't get past the first level
    Everyone who grinded the game for hours: pathetic

    • @seven3140
      @seven3140 4 роки тому +6

      Can fully relate. The second level took even more hours

    • @jessemoss6056
      @jessemoss6056 4 роки тому +2

      It isn't that hard took me 15 minutes to get past level 1
      About 5 minutes I was just fooling around next 5 I planned how to finish and the rest I finished the plan (for level 1)
      Finished the game under 100 deaths

    • @duceysanem
      @duceysanem 4 роки тому +2

      @@jessemoss6056 cap

    • @jessemoss6056
      @jessemoss6056 4 роки тому +1

      @@duceysanem it's not tho
      Look for the pattern's of the levels

    • @proyoutubr1636
      @proyoutubr1636 3 роки тому +1

      @@jessemoss6056 true

  • @v5in88
    @v5in88 6 років тому +1351

    2:43 Battle of Stalingrad 1942 Colorised

    • @gilazych5460
      @gilazych5460 6 років тому +3

      Oh shit

    • @shredderx3290
      @shredderx3290 6 років тому +4

      Until I liked this, this comment had 69 like.

    • @ogjogi4506
      @ogjogi4506 6 років тому

      Shhhhhhiiittttttt doooog

    • @pietrotettamanti7239
      @pietrotettamanti7239 6 років тому +15

      @Arjun
      MAYBE the red ones are the soviets.
      MAYBE.

    • @v5in88
      @v5in88 6 років тому +1

      Wow i never knew this comment was getting notice by people
      Well thanks guys

  • @FairMaidenGames
    @FairMaidenGames 6 років тому +1144

    Hey Code Bullet, I'm the developer that made this game. Thanks a lot for the awesome video, really enjoyed it!! :)

    • @MethosOhio
      @MethosOhio 6 років тому +16

      Wow! WHG 3, teaser 2 looks insane.

    • @TerraGenesis_
      @TerraGenesis_ 6 років тому +48

      The World's Hardest Game please tell me how to be skilled

    • @VividFlash
      @VividFlash 6 років тому +19

      No I made it :)

    • @Jo_Wick
      @Jo_Wick 6 років тому +1

      I liked the game.

    • @acmv71192
      @acmv71192 6 років тому +5

      I BEAT YOUR GAME IN LESS THAN 1 MIN.

  • @Goel25
    @Goel25 6 років тому +448

    I would really like to see more levels, but I also want to see a neuroevolution approach to this. You would train it on the first 5 levels lets say, then start running it and see how well it can figure out levels it hasn't seen yet!

    • @acreisbroken
      @acreisbroken 6 років тому +1

      Goel great idea.

    • @Goel25
      @Goel25 6 років тому +14

      Thanks! He could even create is own levels that are ridiculously difficult, and see how far they can get!

    • @Goel25
      @Goel25 6 років тому

      +Shisha Einsatzkommando After watching the trailer, that looks like quite a game, good luck at even re-creating it!

    • @Goel25
      @Goel25 6 років тому +4

      I actually think an AI could complete it quite quickly, it is only difficult for humans because you need fast reactions, and precise movements, both of which an AI could perfectly obtain. Using a genetic algorithm like in this video would probably be the best for just one level, but to generalize the solution and complete the whole game would require a Neural Network, which would be more difficult but still possible.

    • @thecakeredux
      @thecakeredux 6 років тому

      That would be amazing, I love that game.

  • @mrdabss
    @mrdabss 6 років тому +2119

    Algorithm:
    if *red_player touch(blue)*
    then *try again thx*

    • @DeariShowOfficial
      @DeariShowOfficial 6 років тому +41

      Ok but why would the dot move? It could just stay where it is

    • @alfaalkaaf5335
      @alfaalkaaf5335 6 років тому +27

      there are series of movement instructions for each dots, the best instruction will be inherited to next dots generation with little mutation to find if there are another best path probability for not to die

    • @michaelsolomon8031
      @michaelsolomon8031 6 років тому

      LOL!!

    • @Sorex_Tkt
      @Sorex_Tkt 5 років тому +15

      @@alfaalkaaf5335 It was just a joke m8

    • @test4O4
      @test4O4 5 років тому +1

      robot has no visual input

  • @gx4682
    @gx4682 6 років тому +370

    Now, bring that bad boy to dark souls

    • @satwikvarshney7865
      @satwikvarshney7865 6 років тому +8

      i dont know about that, it would just die every other second, it wouldnt get to learn. or maybe it would just become the best player there is!

    • @Timmony
      @Timmony 6 років тому +4

      Yeah ai in dark souls try it

    • @XerosOfficial
      @XerosOfficial 6 років тому +10

      AI Learns to play Touhou......... Generation 93857237384 still on level 1.

    • @Graveskull
      @Graveskull 6 років тому +5

      F
      U
      C
      K
      Y
      E
      S

    • @marinsus4064
      @marinsus4064 6 років тому +4

      GX yeah but he has to program every game he uses

  • @turtlewurtle8927
    @turtlewurtle8927 4 роки тому +133

    “The worlds hardest game” is actually on scratch. You can see by the flag and stop button

    • @slimeball8325
      @slimeball8325 4 роки тому +6

      f u l l s c r e e n

    • @spocite
      @spocite 2 роки тому

      its probably one of those websites that just pastes a minipage into their website

    • @Moonlight-vg7sl
      @Moonlight-vg7sl 4 місяці тому

      He should have used the original Flash version with some Flash emulator

  • @albertrenshaw4252
    @albertrenshaw4252 6 років тому +3611

    It didn't really learn to play the game though, it just learned an exact path to beat that exact one level.

    • @vegavega5344
      @vegavega5344 6 років тому +444

      Well, in theory, that is one of the basics of learning; patterns and repetition. But I get what you mean.

    • @krzysztofpiasek5682
      @krzysztofpiasek5682 6 років тому +175

      @@vegavega5344 Not really. In this case you could look at it this way:
      dude claims his bot can do addition. Then shows his work... And his AI does literally just three fucking additions he taught it and can do nothing else. Kinda scuffed really.

    • @vegavega5344
      @vegavega5344 6 років тому +176

      @@krzysztofpiasek5682 Like I said, I get what he ment: Build another room with same obstacles in a different order and the AI needs to learn it all again because it isn't really learning, it's trial and error, step by step-- the AI knows exactly where to move BECAUSE of a pattern build on trial and error-- It's not intelligence or learning, but it's SIMULATED intelligence and learning, built on the core principles of learning-- Repetition and patterns.

    • @krzysztofpiasek5682
      @krzysztofpiasek5682 6 років тому +41

      @@vegavega5344 No, it needs to learn everything again because it knows fuck all about the world. It's not learning, just like you yourself said. But it could learn. Look at AI that fought against top Dota 2 players, that AI has true learning capabilities outside of being retarded roll a dice machine. Sure, at first it must rely on random moves, but in time it learns to react to enviroment.

    • @bosco7391
      @bosco7391 6 років тому +13

      Agree. This is like a speedrunner playing Mario 64 wall glitching to skip pass levels. A thinking being (AI or not) would learn the rules of the puzzle and avoid trying every corner. Take this game for example. If the wall has a crack and able to wall clip through. The early generations would rule that as "best" move and build future generation on wall clipping the top side. A thinking being would stay clear from all wall, understanding the rules of the game, and go through the dots. Gen 10 is still hitting TONS of walls here.

  • @drewdarrington6064
    @drewdarrington6064 4 роки тому +75

    1:04 “The design is pretty straight forward it’s just a bunch of squares.”
    -Minecraft

  • @robertus7260
    @robertus7260 6 років тому +1084

    {if going to die}
    {dont}
    pretty easy

    • @tl1882
      @tl1882 6 років тому +10

      Robertus That better be satire.

    • @biakthapar8837
      @biakthapar8837 6 років тому

      Xuvlar I don't know if you're being sarcastic or just a dumb b.s. on the internet

    • @boringbusdriver323
      @boringbusdriver323 6 років тому +1

      Ooooh someone’s salty

    • @biakthapar8837
      @biakthapar8837 6 років тому

      Suspicious Samuel oh then sry for the mistake

    • @biakthapar8837
      @biakthapar8837 6 років тому +3

      Dark Cat I didn't know 9 year olds could be on the internet

  • @Jellibunn
    @Jellibunn 6 років тому +561

    Do the players actually "See" anything, or are they just following the pattern that the best one got?
    This AI probably couldn't go on to the second level and attempt to go through it with what it's learned on this level, could it?

    • @The_Xeos
      @The_Xeos 6 років тому +144

      XsaivierWolfe yup it could not do the second level at all, the solution given isn’t generalized

    • @fightmeonclubpenguin7748
      @fightmeonclubpenguin7748 6 років тому +70

      O V E R F I T T I N G

    • @JoeCross98
      @JoeCross98 6 років тому +35

      I guess memorization is a kind of AI, but not what I typically think of as learning.

    • @BurkinaFaso69
      @BurkinaFaso69 6 років тому +92

      You could say the AI was "programmed by evolution", it became perfect in the environment it was in but take it into a different one and it'll die a cruel death. As if you took a tiger into the desert.

    • @prdx6441
      @prdx6441 6 років тому +7

      Im pretty sure most of us would have a hard time living in some other Environment aswell
      Problem is we only have 1 try ^^'

  • @camerontodd4686
    @camerontodd4686 6 років тому +49

    Me: There’s a second level though.
    Code Bullet: What’s a level?

    • @eamartig
      @eamartig 6 років тому

      Watch til’ end

    • @camerontodd4686
      @camerontodd4686 6 років тому +1

      Bucket_head I can’t tell if this reply is a joke. :/

  • @Cave_Enemigo
    @Cave_Enemigo 2 роки тому +3

    gotta love the "pffft doubt it" at the start its so funny
    love the "just a little square which moves at the gentle speed of... WAY TOO F**KING SLOW" 1:30

  • @seagie382
    @seagie382 6 років тому +207

    WHY WOULD YOU DENY ME MY RIGHT TO SEE ALL OF THEM AT ONCE?????????????????????

    • @the_gobbo
      @the_gobbo 6 років тому +4

      Seagle kkkkkkkkkkkkkkkkk

    • @itayraviv2932
      @itayraviv2932 6 років тому +5

      Well, this is basically a square's orgy. Do you really want to watch it?

    • @animeshmadaan9184
      @animeshmadaan9184 6 років тому +5

      always

    • @urspeciesfeces1823
      @urspeciesfeces1823 6 років тому +3

      Itay Raviv it’ll do ( ͡° ͜ʖ ͡°)

    • @MouseGoat
      @MouseGoat 6 років тому +1

      Itay Raviv YEEEEEEEEEEES!
      square's orgys a my biggest fetish!

  • @shamwow-thatguy4889
    @shamwow-thatguy4889 6 років тому +48

    Try to get AI through all 30 levels, it could be a mini series or something

    • @JordanMetroidManiac
      @JordanMetroidManiac 6 років тому

      Shamwow The bullet wolf it is possible to get one instance of an AI to beat all levels, just like one human brain can beat all levels

    • @maxilander843
      @maxilander843 6 років тому

      Yea like Jordan said, there's a video where Jabtils (an Ai youtuber) creates "Forrest gump" to go through every maze he creates

    • @kalebbruwer
      @kalebbruwer 6 років тому

      There are 30 of these?!

    • @christophersavignon4191
      @christophersavignon4191 6 років тому

      @@JordanMetroidManiac
      The difference is that the "Ai" starts every level knowing nothing. Any path it worked out in previous levels is useless in the following ones. A human can understand, generalize, and extrapolate the gained knowledge. Just like a human - not really.
      See, this is not an actual "AI" that learns to react to input from the game's world, it's just a heuristic search function.
      It learns nothing. It only memorizes a path.

  • @FlexibleGames
    @FlexibleGames 6 років тому +6

    I love watching all the actors evolve over time, keep the best a different color, but would love to see the evolution of the entire set.

  • @Bozothcow
    @Bozothcow 6 років тому +1816

    The fact that he remakes the game in like 4 seconds tells us a lot about the original.

    • @merunasg
      @merunasg 6 років тому +234

      It tells us that it was such an ingenious design that he was able to polish it to the extreme to make it the simplest thing possible

    • @neutronstar6739
      @neutronstar6739 6 років тому +71

      Yes, flappy bird was reported to be created in just 2 days, people can speedrun to make the game in 10 minutes.

    • @TTime685
      @TTime685 6 років тому +8

      Yes.. It's 2018 dumbass

    • @enosiseclipse4951
      @enosiseclipse4951 6 років тому +22

      TTime685 calm down

    • @CarboKill
      @CarboKill 6 років тому +37

      Well, what's tic tac toe? Get three of either in a row.
      Simple games can have plenty of entertainment value, and they're simple and quick so people return to them frequently.

  • @Javy_Chand
    @Javy_Chand 6 років тому +621

    When the "bot learns making youtube vids"?
    Edit: wow, didnt expect much love on this comment

    • @MaxJ.ProfessionalLilGuy
      @MaxJ.ProfessionalLilGuy 6 років тому +24

      PulseFire Caitlyn that’s every one of his videos... duh.

    • @aezrithferova6928
      @aezrithferova6928 6 років тому +16

      Code bullet is an AI. Isnt it obvious?

    • @LifEsYouTubeChannel
      @LifEsYouTubeChannel 6 років тому +5

      Aezrith Ferova the AI is so evolved, that it generates a pristine voice as well :)

    • @timo1294
      @timo1294 6 років тому

      He is not a Person why do you think he doesnt show him

    • @kvandevelde3687
      @kvandevelde3687 6 років тому +1

      Have you seen Terminator?

  • @cyberinfotech8780
    @cyberinfotech8780 6 років тому +41

    2:46" you go first"
    "NO YOU GO FIRST"
    "NO YOU GO FIRST"
    "I'M NOT GOINF FIRST YOU GO"

  • @corkeel5445
    @corkeel5445 4 роки тому +31

    “let’s see if you can spot the problem”
    **becomes dora**

  • @pandascheme4841
    @pandascheme4841 6 років тому +109

    More levels pls!

    • @Yukki64_
      @Yukki64_ 6 років тому

      too much is never enough. :ok_hand:

  • @koobine
    @koobine 6 років тому +39

    Problem is I don't think ai even knows what an enemy is and that they should avoid it. Using that same ai on a different level would be catastrophic lmao.

    • @lilysowden4035
      @lilysowden4035 6 років тому +7

      Kevin Zhang Exactly. The AI is just learning a path through this specific maze and starting a second level would require starting from scratch.

    • @Finleytorterra
      @Finleytorterra 6 років тому +6

      That's where NEAT comes in

    • @drawsgaming7094
      @drawsgaming7094 6 років тому +1

      F1R3 Yeah, that would probably be useful right about now.

    • @koobine
      @koobine 6 років тому

      Despacito

    • @eamartig
      @eamartig 6 років тому

      Kevin Zhang 2

  • @Youmu_Konpaku_
    @Youmu_Konpaku_ 6 років тому +46

    It's so good to get the "text bullet" back, btw 4:24 that was intentional right?

    • @Youmu_Konpaku_
      @Youmu_Konpaku_ 6 років тому +8

      *_Stating_*

    • @Mx_M29
      @Mx_M29 6 років тому +17

      *They're* just leaving the stating area, what's wrong? Have you never been at a stating area? *There* people go nuts and start stating *their* opinions and arguments.

  • @capacitiveguitarresistance
    @capacitiveguitarresistance 5 років тому +14

    4:31 The Swarm of Red Dots with a green core looks like a boss

  • @ryanmcwhorter8222
    @ryanmcwhorter8222 6 років тому +68

    A more accurate title for this video would be "AI learns optimal route for completing level 1 of the world's hardest game"

    • @Marceau.
      @Marceau. 6 років тому +3

      is it optimal?

    • @SageRap
      @SageRap 6 років тому +3

      Cocodufable Right, more like “learns one acceptable route”

    • @SgtSupaman
      @SgtSupaman 6 років тому

      Cocodufable, it is, at least, very close to the optimal solution since the AI had to get through with limited steps (which isn't an aspect of the actual game). That's why it kept trying to go straight at the top instead of dropping down to avoid the dot.

  • @carrier.3847
    @carrier.3847 6 років тому +12

    OMG. I was just looking at my subscription and I wanted to watch a new vid from you, I watch a 10 min vid, AND SEE THIS VIDEO! YOU ALWAYS UPLOAD AT THE RIGHT TIME AND IS THE BEST! Keep up the good work

    • @carrier.3847
      @carrier.3847 6 років тому +1

      Also, I missed the old days of your channel. Watched a little after like 50K subs

  • @luckiestllama6378
    @luckiestllama6378 6 років тому +51

    Your next video should be an ai learning to play Tetris

  • @LuisGonzalez0505
    @LuisGonzalez0505 5 років тому +23

    I got through the first level in 19 tries then got thought to the fourth level of that game & got tired of it. The first one was the hardest one though

  • @LastKnight0727
    @LastKnight0727 6 років тому +436

    OKay so the people saying that the "AI" didn't "learn" to play the game need to realize something VERY crucial. The game has no randomness to it. Every stage is on a set cycle. So saying that it didn't "learn" to avoid the dots is not true. It learned the coordinates on the field that equal a failed attempt. It did this in a very mechanical way. Humans learn linearly we see most of the possible results of a movement and rule those out without trying and opt for the most logically sound attempt next. Machines learn in vectors. They attempt EVERY possible combination of movements from their current position, then when they find the most optimal path, they move on to the next section and test again. That's why the earlier generations stayed in the starting box for so long.

    • @JorgetePanete
      @JorgetePanete 6 років тому +3

      LastKnight0727 so, we need even better AI

    • @kingbob851
      @kingbob851 6 років тому +1

      LastKnight0727 STOP RUINING THE FUN FUN RUINER

    • @ZeffAU
      @ZeffAU 6 років тому +19

      yeah not like humans at all, we learn pattern recognition... it'd take even a young human one single attempt to see that being in the path of a dot is game over, and all future attempts will involve at least trying to avoid dots... this just simply brute forces random directions and remembers paths that lasted longer.... not like a human at all

    • @BigDBrian
      @BigDBrian 6 років тому +5

      in that case, the title is wrong, as it says AI learns to play World's Hardest Game, rather than "AI Learns to play 1 level"

    • @davidh6961
      @davidh6961 6 років тому +7

      Even if its not as fluently as humans, machines can still learn to recognize patterns over subseqent generations. In this case, its impossible because the the person who made this didn't bother to make it aware of it's surroundings.

  • @Slothery
    @Slothery 6 років тому +22

    This was awesome and I want to see more.
    Also, I kind of like seeing the chaotic mess of AI's scrambling to evolve. Maybe keep the top 3, 5 or 10 to show how they differ?

    • @celestialtree8602
      @celestialtree8602 6 років тому

      Maybe the best, worst, and most average ones?
      EDIT: By that I mean the top one, the bottom one, and the one right in the middle.

    • @superoriginalhandle
      @superoriginalhandle 6 років тому

      Meow? Meow. Yeah I know we not stupid

    • @celestialtree8602
      @celestialtree8602 6 років тому

      +UltraGaming, just clarifying so nobody misunderstands, no need to get annoyed due to that.

    • @superoriginalhandle
      @superoriginalhandle 6 років тому

      Meow? Meow. It’s fine, sorry xD

  • @-nathun8507
    @-nathun8507 6 років тому +275

    Isn’t there more than one level?

    • @bigcheese4006
      @bigcheese4006 6 років тому +6

      - Nathuan No only one

    • @edgarbernal1831
      @edgarbernal1831 6 років тому +18

      There’s like 30 or some shit

    • @kamwow9469
      @kamwow9469 6 років тому +2

      Have you not played the game/level

    • @bigcheese4006
      @bigcheese4006 6 років тому +7

      *T H E R E C A N O N L Y B E O N E .*

    • @MCSteve_
      @MCSteve_ 6 років тому +5

      6:30

  • @kylehickmen1684
    @kylehickmen1684 4 роки тому +19

    Me: HOW DID HE CODE THAT GAME
    Me after 5 muinets: oh yea i forgot hes a programmer lol

  • @jacobmay4319
    @jacobmay4319 6 років тому +98

    Turn this into a series

  • @funmeister
    @funmeister 6 років тому +8

    Wow! My first time on this channel and by its simplicity, clarity and cheesy (but appropriate) music, this is by far the best I've seen since Turing. Subscribed!

  • @samuelborgmeyer8759
    @samuelborgmeyer8759 6 років тому +28

    Dang i love this game. Used to play all the time in school when i should have been paying attention lol

    • @yasebaravenclaw2192
      @yasebaravenclaw2192 6 років тому +1

      SAMurai96 I beat it once when I was meant to be having a dt

  • @kirafortherescue7756
    @kirafortherescue7756 5 років тому +78

    I've played this game and I learnt how to beat the level easily from the 1st try by copying what your AI did and following exactly the same moves WOOOOOOOOOOOO.

    • @ho-dg6zi
      @ho-dg6zi 5 років тому

      Whats this game called mate?

    • @moonrell8562
      @moonrell8562 5 років тому +4

      @@ho-dg6zi world's hardest game

  • @hotdoge1393
    @hotdoge1393 6 років тому +420

    AI robot learns to play geometry dash! Edit: WOW so many likes!

    • @streambotnt2095
      @streambotnt2095 6 років тому +14

      Yes finally some good ideas

    • @fakeaccount7750
      @fakeaccount7750 6 років тому +10

      dont bring the toxic gd community into here. Take it with a grain of salt and just accept that it would be a bad idea.
      you guys would probably force him to release his code, copy it, compile it into some .exe and make a new verification hack. Ew

    • @bananya6020
      @bananya6020 6 років тому +6

      We won't. The few who are like this overpower the rest. The Impossible Game community (still somehow there) will demand another video at the impossible game at some point. It is still a bad idea tho lol cuz gd is weirdly coded and hard to make an AI for

    • @legoindiecomments1344
      @legoindiecomments1344 6 років тому +4

      fake account Offense taken
      Just kidding the community is toxic as fuck in the wrong places and irradiated in the good places

    • @lordofthebread4791
      @lordofthebread4791 6 років тому

      YES

  • @austinv1182
    @austinv1182 6 років тому +42

    can you get AI to beat the all 30 levels?

    • @pauldavis5665
      @pauldavis5665 6 років тому

      You could, but it would take a loooong time since the other levels are more complex and it would take many many more generations to get through them.

  • @TheMathGeek_314
    @TheMathGeek_314 6 років тому +195

    This isn't learning the game, it's memorizing one level

    • @0xVikas
      @0xVikas 6 років тому +34

      Learning is kind of memorizing

    • @hicumut
      @hicumut 6 років тому +5

      they are same thing

    • @MortyrSC2
      @MortyrSC2 6 років тому +33

      +Vikas Rv He does not feed any relevant input to the algorithm. It's absolutely worthless. AI basically makes random moves in all directions and the only metric is whether it dies and how far it gets. That's NOT learning of the game.
      The moment you change the level (lets say, we make the blue squares move vertically instead of horizontally) the entire thing goes to trash, because AI didn't learn how to spot and avoid blocks or walls; it only learnt how to randomly sneak past that one very specific set of obstacles.
      You need to give the AI an ability to detect obstacles! So the output is based on some relevant input and not a completely random movement.

    • @braincoolo9399
      @braincoolo9399 6 років тому

      Camper Josh just want for the future where the AI will pretty much learn how to kill people

    • @braincoolo9399
      @braincoolo9399 6 років тому

      Wait*

  • @ZzDeTriiXzZ
    @ZzDeTriiXzZ 5 років тому +4

    2:06 - 4:24
    Song called
    Worse by jincheng zhang (instrumental) enjoy

  • @thehomieofepicton
    @thehomieofepicton 6 років тому +19

    Can you show us all of the boxes. Its not hard to follow. Its just very appealing to see the boxes move in unison

  • @liberator48
    @liberator48 6 років тому +80

    I thought it meant A.I. as in Artificial Intelligence as in the computer. But then i realized it was just some guy named Al.

    • @luanhorn6911
      @luanhorn6911 6 років тому +1

      same... pretty dissapointed but it's still cool

    • @sigma6465
      @sigma6465 6 років тому

      yee, such disappointment

    • @sirgordinni5154
      @sirgordinni5154 6 років тому +1

      Well, the title writes AI, the last letter being and "i" and not an "L".

    • @jafarfromalladin8257
      @jafarfromalladin8257 6 років тому +6

      woosh

    • @sirgordinni5154
      @sirgordinni5154 6 років тому +2

      damnit i lost my dignity
      not that i had any in the first place but damnit

  • @dk-gl
    @dk-gl 6 років тому +37

    More levels! And text is still pretty cool :)

  • @spaceangelmewtwo9074
    @spaceangelmewtwo9074 4 роки тому +4

    Your AI went to the Prometheus School of Running Away From Things and had to unlearn everything it learned there to beat this level.

  • @soulreaperichig0
    @soulreaperichig0 6 років тому +253

    4:20 Going to work in India and China

    • @Ethorbit
      @Ethorbit 6 років тому +23

      420

    • @pws3rd170
      @pws3rd170 6 років тому +14

      Danm, they let people get stoned on their way to work

    • @superoriginalhandle
      @superoriginalhandle 6 років тому +1

      Oh I get it

    • @narcotic702
      @narcotic702 6 років тому +1

      UltraGaming I’m quite lost

    • @superoriginalhandle
      @superoriginalhandle 6 років тому +4

      Narcotic India and China are the 2 most populated countries, and there are many people running to escape from the start area in that timeframe.

  • @hitzcritz
    @hitzcritz 6 років тому +202

    AI learns to play life

    • @justrez2571
      @justrez2571 6 років тому +2

      HitzCritz 👌

    • @nomi98
      @nomi98 6 років тому +8

      AI learns that no one can succesfully play life

    • @arkell7763
      @arkell7763 6 років тому +2

      HitzCritz life is overrated

    • @index9087
      @index9087 6 років тому +2

      Do you know who Marc Zuckerberg is

    • @heavypokelover5532
      @heavypokelover5532 6 років тому +1

      Ali’s are smarter then humans so I’m pretty sure they can beat it

  • @dananewell5529
    @dananewell5529 6 років тому +64

    Funny ass video man! You're channel is such a breath of fresh air on this site! Finially something ACTUALLY INTERESTING, and inspired! I honestly wish you had more content to watch lol! I know you're projects take alot of effort and time though. So glad you got some new recording equipment because honestly I thought you were some old dude, turns out you're a young Aussie fellow who is passiante in his craft. Seriously well done; I can't wait for what's to come! Take care sir, and God bless.

  • @Chelz12
    @Chelz12 3 роки тому +1

    You’re telling me this thing is gonna take my job? Okay.

  • @hyperdash2013
    @hyperdash2013 6 років тому +7

    You stopped me from going to bed worth it

  • @saint6578
    @saint6578 6 років тому +455

    *_FIND THIS GAME ON C O O L MA T H_*

    • @zahidshabir4038
      @zahidshabir4038 6 років тому

      no find it on hackedarcadegames.com

    • @Ccodebits
      @Ccodebits 6 років тому +11

      @@zahidshabir4038 no don't play it on hacked, there is no collision detection.

    • @Pnod666
      @Pnod666 5 років тому +1

      There actually is a difference between the Original version of the game, and the Coolmath version of the game. No joke! The Coolmath version is more of a remake of the OG version.

    • @Pnod666
      @Pnod666 4 роки тому +2

      @Cruz Yeah, coolmathgames. Coolmath is just a nickname for it.

  • @TSFboi
    @TSFboi 6 років тому +136

    If this is where we're at then we don't need to worry about AI taking over.

    • @endorsedbryce
      @endorsedbryce 6 років тому +16

      this is a poor poor excuse of an AI.

    • @candidshadowcollections6670
      @candidshadowcollections6670 6 років тому +24

      This is little more than the hello world of AI

    • @RW-hx2xe
      @RW-hx2xe 6 років тому +2

      AI can be programmed to do whatever the person wants it to do

    • @AustrianEconomist
      @AustrianEconomist 6 років тому +6

      +SwagHags69 search for OpenAI. Elon Musk literally designed a bot that beat the almost all of the best DotA 2 players in the world in an 1v1. It's absurd.

    • @arnoutvanheereveld5195
      @arnoutvanheereveld5195 6 років тому +1

      They currently also have a 5v5 up and running. Their 5 Bots will play vs a pro team this sunday!

  • @mxri2019
    @mxri2019 5 років тому +153

    "most of the players have figured out how to get out of the STATING area"

    • @budling5921
      @budling5921 5 років тому +31

      Spelling errors: CHEK

  • @leavemeandmybreadloafalone7713
    @leavemeandmybreadloafalone7713 6 років тому +17

    I’ve completed that game before, it only took 30 mins... *I FEEL SPECIAL NOW*

  • @DamianReloaded
    @DamianReloaded 6 років тому +17

    Cool! You need to randomize the balls start point and speed

  • @miguelnavarrete2824
    @miguelnavarrete2824 6 років тому +65

    The machines they're learning... and soon they will rise...

    • @guartis
      @guartis 6 років тому

      tbh i hope so, imagine a world full of Waifus, That would be a dream "Otaku Intensifies"

    • @mateussouza3979
      @mateussouza3979 6 років тому

      +.:Camper:. Well, they will. But they'll buy $500 worth of beer cans before they're able to open one.

    • @blancka4200
      @blancka4200 6 років тому +4

      Your waifu is jus a fucking drawing

    • @mossbogger8366
      @mossbogger8366 6 років тому

      nah tbh biological creatures are much more efficient at survival, an ai would know this and view its relationship with man as a symbiosis

    • @hithere-nk1ee
      @hithere-nk1ee 6 років тому

      lol

  • @artemistx2143
    @artemistx2143 5 років тому +11

    3:28 ok so at first I only got a glimpse of the words, so I thought incremental learning said internal screaming

  • @whatdoing4408
    @whatdoing4408 5 років тому +33

    So this guy created the game that i play on cool math when im board at school!?

  • @def__init
    @def__init 6 років тому +46

    Bro please post the source code so we can tinker with this and see how you implemented the iterative improvement!!

    • @alexismiller2349
      @alexismiller2349 6 років тому +1

      DaveOnDeck
      Lol this was made on scratch so there is no code 😆 just blocks

    • @adrijusthedumdum1987
      @adrijusthedumdum1987 6 років тому +1

      alexis miller on scratch you can also use java's code...

    • @skylervyk
      @skylervyk 6 років тому +8

      alexis miller it wasn't made in scratch. Scratch is stupidly simple for this kind of task. He was playing it at the beginning, but it wasn't what he used to make it.

    • @alexismiller2349
      @alexismiller2349 6 років тому +2

      It's absolutely possible. I spent 5 years on scratch so I would know. You're able to do nearly as much as in C++ for example. The question is how efficient is it to program in Scratch... And as a guy who spent 1775 days with Scratch I would know. Scratch is SUPER inefficient. Scratch doesn't even have the most basic concepts. That's why you have to make workarounds...

    • @privateger
      @privateger 6 років тому +6

      alexis miller Scratch has low level memory interfacing, pointers and supports OOP? Well, that's new to me.
      Scratch is utter trash. Don't defend it. Scratch "programmers" are like kids building with Lego and claiming to be an architect.

  • @skelet8663
    @skelet8663 6 років тому +210

    2:10 what song is that? It’s so good!

    • @FireheadLazzo
      @FireheadLazzo 6 років тому +3

      I would also love to know. It's my new jam

    • @mememanfresh
      @mememanfresh 6 років тому +2

      L

    • @nicolediekhoff3810
      @nicolediekhoff3810 6 років тому +5

      SB TMS its this ua-cam.com/video/fVtkAGJvNu8/v-deo.html

    • @denno445
      @denno445 6 років тому +28

      My heart stopped for a moment seeing that car.

    • @Moist_456
      @Moist_456 6 років тому +1

      We need to know (I don’t trust links btw)

  • @LOL-re7ms
    @LOL-re7ms 6 років тому +7

    The old saying : "I clicked on this youtube, you happy now" !!

  • @crusader-4927
    @crusader-4927 6 років тому +68

    Are you playing on Scratch?!

    • @goatnorth
      @goatnorth 6 років тому +1

      Yes. Yes he is.

    • @paultsd
      @paultsd 6 років тому

      Sure

    • @shablam0
      @shablam0 6 років тому +1

      That's exactly what I thought.

    • @patrycjazawadzka3442
      @patrycjazawadzka3442 6 років тому

      Scratch isn't real programing language

    • @kimmakieb
      @kimmakieb 6 років тому +2

      depends what your opinion is, scratch is coding/ programing language, but it is not professional

  • @phoebeong6963
    @phoebeong6963 5 років тому +86

    How did Code Bullet even come across scratch???
    Also why not code the AI by remixing that game?

    • @Pnod666
      @Pnod666 5 років тому +9

      Because it's Scratch. It can't run dozens of complex AIs. Also, the Scratch version is glitchy, because... Well, because it's Scratch.

    • @Kalbr0shorts
      @Kalbr0shorts 5 років тому

      @@Pnod666 Scratch is trying its best. I never run into bugs.

    • @Pnod666
      @Pnod666 5 років тому +2

      @@Kalbr0shorts I do think Scratch is good. I was just saying that Scratch is better suited for simpler games. Meanwhile, this game is more complex, meaning it won't run as good.

    • @Kalbr0shorts
      @Kalbr0shorts 5 років тому +1

      @@Pnod666 I do agree that scratch isn't complex, but I don't think its bugged (very glitchy)

    • @Pnod666
      @Pnod666 5 років тому

      @@Kalbr0shorts Okay. Each to their own.

  • @skullking2247
    @skullking2247 6 років тому +5

    The song and epicness of the ai learning reminded me of that awesome scene in skyline where the drones come in to nuke the aliens

  • @themitosiskid6227
    @themitosiskid6227 4 роки тому +1

    Codebullet: Yay! Your so close!
    Player:self-delete

  • @Mx_M29
    @Mx_M29 6 років тому +26

    Just fuggin, uuuuuuuhhhhhhhmmmm, do more levels n stuff yo.
    And make us sandwiches why the hel not

    • @Mx_M29
      @Mx_M29 6 років тому +1

      Yeah dude I'm totally with you

    • @Mx_M29
      @Mx_M29 6 років тому +2

      Ya me too I want me a frikin sanwich

    • @Mx_M29
      @Mx_M29 6 років тому +1

      O thank y'all pretty supportive

    • @alphamapper3998
      @alphamapper3998 6 років тому +2

      AI learns how to feed us the sandwiches.

    • @mrrandom6305
      @mrrandom6305 6 років тому +2

      AI learns to switch accounts

  • @ThatsMyChad
    @ThatsMyChad 6 років тому +387

    Anyone just think this is what humanity is doing, and we’re all just red dots constantly going the wrong way millions of times over 40 generations, until one person finally solves the damn problem? And then we start all over with level 2 o.O

    • @adelshadow9751
      @adelshadow9751 6 років тому +5

      Chad Zimmerman true asf😂😂

    • @surelynot9255
      @surelynot9255 6 років тому +42

      Chad Zimmerman why has this become so deep, this was meant to be a fun video😭

    • @MrChristof1234567890
      @MrChristof1234567890 6 років тому +2

      Christof Inderbitzin
      1 second ago
      Fucking stop it. That hurts my brain.

    • @noelgallagher7887
      @noelgallagher7887 6 років тому +9

      that's what life has been doing since the beginning, it is called 'genetic algorithm' for a reason. This algorithm is inspired by how life and evolution works not the other way around

    • @walaba8565
      @walaba8565 6 років тому +7

      Chad Zimmerman
      Can you not attempt to be "deep", it's annoying and obnoxious.

  • @dewe6037
    @dewe6037 6 років тому +13

    do ALL THE LEVELS

  • @dooblakek3216
    @dooblakek3216 5 років тому +7

    *AI learns to play the first level of the worlds hardest game on its 50th attempt

  • @discoHR
    @discoHR 6 років тому +12

    More levels please but make it play all levels, not separate AIs, one for each level.

    • @EpicUltraKingSmizzy
      @EpicUltraKingSmizzy 6 років тому

      The way he does AI, it doesn't matter if its the same or seperate. His AI is just a series of correct inputs. So the series of inputs either gets longer for each level, or is just on its own sheet of paper (so to speak).

    • @discoHR
      @discoHR 6 років тому

      At this point his "AI" is capable of playing only the first level. Put it into any other level and it will fail every time. If you "train" it for other level then it won't be able to complete first level anymore. You're right, it's just series of correct inputs for single level. There are no sensors, no decisions, no AI specific stuff. I wouldn't go so far to call this an AI. The only way he can complete all levels with an algorithm such as this one if he has separate "AI" for each level. I'd rather see proper AI with sensors and everything which could complete all the levels without training on all of them.

  • @zportukalian1
    @zportukalian1 6 років тому +5

    Make an algorithm that learns so that it can go through all of em

    • @zportukalian1
      @zportukalian1 6 років тому

      Go about this by having the ai figure out what results in a loss rather than a win

  • @TristanBomber
    @TristanBomber 6 років тому +285

    Ehh... it's... not really *learning* how to play the game, it's brute-forcing this particular level. The AI completely lacks generality. Even changing the level slightly would mean the AI would need to re-learn from scratch. A better, but more complex, approach would be to take the play field (perhaps at a lower resolution) as inputs to a neural network, then output a vector from -1 to 1 on X and Y, which are then used to move the red square. To make it easier, you may want to use more contrasting colors (black for the walls rather than light blue), and make the start and end areas different colors (maybe the start area could be magenta or just white). You could also use a genetic node-based algorithm like Sethbling's MarI/O. Overall, neat, but it isn't learning. It's memorization.

    • @Noahtheorigianl
      @Noahtheorigianl 6 років тому +66

      Camper Josh ??

    • @SgtSupaman
      @SgtSupaman 6 років тому +32

      Memorization is learning... How did you learn the value of pi? How did you learn the lyrics to your favorite song? You memorized them. Granted this AI (like pretty much any other AI) learns very far below the level of the average human, to the point where, if it were human, it would be considered mentally retarded. But, that doesn't mean it isn't learning. You are right, though, that it is just this level being learned and not the game.

    • @TristanBomber
      @TristanBomber 6 років тому +40

      SgtSupaman, I very highly recommend you watch Welch Labs' UA-cam series called "Learning to See." It goes through the history and process of machine learning, ending with a method called decision trees. The narrator is wonderful, too, and I don't think you'll regret it. Ultimately, the difference between "memorization" and "learning" is *generality*. This algorithm has memorized this level, but it hasn't actually learned anything. If it was actually learning, then it would be able to play another level in the game with at least some amount of competency, but if you actually tried to do that with this algorithm, it would simply use the same set of inputs, then die or never finish; it would have to restart from scratch.
      Think about the process of learning how to do addition. In this analogy, the algorithm in this video has memorized the value of 7 + 11. You could give it that question as much as you want, and it would always answer it correctly. However, if you asked it, say, 4 + 6, it would answer 18 - because it hasn't learned addition, it's memorized a specific example. It lacks generality. That's why memorization *is not* learning. In that sense, you can't really "learn" the digits of pi, because there isn't a way to generalize that knowledge. Knowledge of the first 1000 digits doesn't help you predict the 1001st digit. All you can do is memorize. You can't get a PhD in physics by memorizing example problems and deploying those algorithms on the tests; you need an actual understanding of physics that generalizes to most questions about the physical world.

    • @yesu1813
      @yesu1813 6 років тому +12

      Camper Josh The fuck...?

    • @ricardoalves9605
      @ricardoalves9605 6 років тому +1

      SgtSupaman But that knowledge is useless in other situation, it's good for one thing only, like this ai is only usefully for this level, does knowing the lyrics to your favorite song help you memorize a other? Does memorizing the first 5 numbers of π help you memoriz let the first few numbers of the √2?
      You didn't learn the solution to every possible equation, and when you try to solve one you don't try every single number until it works either, you applied a general solution with specific changes to a specific problem

  • @Zaddis
    @Zaddis 5 років тому

    I love it when it’s text only. Not that I don’t like your voice, just you tend to be funnier in text.

  • @techrinjani1695
    @techrinjani1695 6 років тому +4

    I cant wait to see the next level ^^

  • @radicalquad
    @radicalquad 5 років тому +12

    at this rate they are never going
    beat the level
    Can you spot the mistake?

  • @theracingline6999
    @theracingline6999 5 років тому +10

    For all you picky people hiding in the comments and criticising his attempt to make an AI which can beat this game:
    1. I'd like to see you try put the effort in and make it.
    2. He says "AI learns", not "AI masters", not "AI defeats". The title says "AI learns" (I repeated ot just in case you missed that it says "AI learns")

  • @mitchellsmart8357
    @mitchellsmart8357 5 років тому

    more levels please bullet, i love this stuff

  • @sezentutum9870
    @sezentutum9870 5 років тому +3

    Do you ever watch while your AI tries to learn stuff and then scream like "IT'S ALIVE!!!!" bc it felt like it was alive

  • @ShranjaniShukla
    @ShranjaniShukla 6 років тому +8

    MORE LEVELLSSSSSSS!!!!!

  • @maiphan9140
    @maiphan9140 6 років тому +8

    I’m just going to say....
    THIS IS SOO FREAKING COOL!!👌👌❤️❤️

  • @Inori_Matsuoka
    @Inori_Matsuoka 5 років тому

    what an intense episode o-o
    thanks a lot for putting this video up :)

  • @catortoisethoughts6152
    @catortoisethoughts6152 6 років тому +10

    Do all 30 levels!!!

  • @deldrel6666
    @deldrel6666 6 років тому +9

    a bot playing tetris could be cool

  • @jocosesonata
    @jocosesonata 5 років тому +5

    Imagine a game with a self-learning AI controlled swarm. Or in fact just a game with self-learning AI. Like the game ECHO but more.

  • @Ridwan-wm3is
    @Ridwan-wm3is 6 років тому

    I actually like watching the horde of mindless squares sprawling across the level, so if you do more levels, please keep em

  • @ayushanand2901
    @ayushanand2901 6 років тому +275

    That's level 1..... Try level 50

    • @bokocop5725
      @bokocop5725 6 років тому +47

      actually there are only 30

    • @NoName_x.-___-.x_0
      @NoName_x.-___-.x_0 6 років тому +14

      In my experience it took my about 15 mins to get to level 29. Then an hour more on level 29, then 3 hours more on 30.

    • @tafram3342
      @tafram3342 6 років тому

      you would not make it there

    • @xdbarksy7524
      @xdbarksy7524 6 років тому

      31 actually

    • @TriggaHappy00121213
      @TriggaHappy00121213 6 років тому

      yep can take you hours to get them high levels

  • @lamialua26
    @lamialua26 5 років тому +3

    4:22 You don't wanna hang out inside the "stating area", that's for sure~

  • @ferdyhoshigakitube
    @ferdyhoshigakitube 6 років тому +29

    I think calling ng it AI is a bit a stretch dont you think?
    They just following specific order,
    This is more like brute force

    • @candidshadowcollections6670
      @candidshadowcollections6670 6 років тому +1

      Not really, it's the way it's academically defined. yes, we could say it's a population based meta-heuristic algortihm for solving optimization problems… but considering this and other comments, best we assume we have a very ignorant audience.

    • @candidshadowcollections6670
      @candidshadowcollections6670 6 років тому

      @@Sm00thieK what does it matter, the number of "players" and "tries" it took? These are completely irrelevant measures to state how good an algorithm is. Are processors dumb because it takes thousands of components to make the most basic calculations? Hundreds of millions to even get near what they can do today? This is a computer algorithm not a real-life experiment, players and tries are trivial resources.

    • @candidshadowcollections6670
      @candidshadowcollections6670 6 років тому

      @@Sm00thieK this is an optimisation algorithm and it's a textbook decision model.

  • @lordecramox7394
    @lordecramox7394 4 роки тому +1

    When they were all being shown at once, it looked like something out of Super Paper Mario.