AI learns to WALK 3D (Part 2)
Get an Exclusive NordVPN deal here: nordvpn.com/CodeBullet It's risk-free with Nord's 30-day money-back guarantee!
WATCH PART 1: • AI Learns to WALK 3D
Twitter: / code_bullet
Patreon: / codebullet
Discord: / discord
Art created by @Dachi.art / dachi.art
Пікірлер: 5 200
Thanks again to NordVPN for sponsoring this video. Get an Exclusive NordVPN deal here: nordvpn.com/CodeBullet It's risk-free with Nord's 30-day money-back guarantee!
@mnatilli9161
Жыл бұрын
BOO!
@ILIKEOTTERS
Жыл бұрын
I will never use nord vpn
@francy3643
Жыл бұрын
code bullet loves money!
@davidjacobsen5898
Жыл бұрын
wait a minute this says 7 days ago
@remianderson6015
Жыл бұрын
First😊
When you started rewarding them for facing the right way, but they just turned their heads and kept walking backwards was like the ultimate "fuck you".
@tweefruitguy2891
Жыл бұрын
So true
@quanphan3669
Жыл бұрын
They like to take a shortcut 😂
@anshik.k.t
Жыл бұрын
Time stamp
@lcajueiro
Жыл бұрын
@@anshik.k.t 16:50
@crelos3549
Жыл бұрын
They followed the instructions exactly as given
AI is finally being added to this AI project, and it only took half of a half hour video of homoerotic character rigging to get this far
@oamioxmocliox8082
Жыл бұрын
;)
@smobasi3367
Жыл бұрын
Code bullet is an ironic name, because the videos take ages to get here
@nokia-gm8gv
Жыл бұрын
fr
@dhpz
Жыл бұрын
Your usual code bullet videos right there
@PembuatKomentarHandal
Жыл бұрын
And We Also Need To Wait Ages For This Series
Idea: co-evolve two AIs in a game of chase. Reward one for catching the other, and one for staying away. See if they learn different walking strategies
@danialrafid
Жыл бұрын
There already is one, search for prey and predator ai simulation on yt
@lui5gif
Жыл бұрын
@@danialrafid yeah but do those just squirm of the floor or prefer to walk backwards like our boys here?
@danialrafid
Жыл бұрын
@@lui5gif It's not 3D, but some of them do walk backwards
@Naokarma
10 ай бұрын
Isn't that literally what the Google AI did to beat DeepBlue?
@franktothemax
5 ай бұрын
Well this should play out just fine in my dreams tonight. Hopefully they all stay the same size
Now you need to make a horror game where throughout the game, the enemies AI progressively gets better and better at walking as they chase you.
@Naokarma
10 ай бұрын
It definitely wouldn't be able to train in realtime, given how many hours it took to train, but you could absolutely train an AI separately and save the state of every generation so that you can have the AI to switch to later generations at certain points. I'm imagining a slenderman-like game, but with a more complex map, and maybe more of them spawn over time?
@unponderable8143
9 ай бұрын
Rainworld
@TAP7a
6 ай бұрын
Especially if they enable the full 180 head turn over time too
@luminous3174
2 ай бұрын
underrated
This guy is the most sane Aussie programmer I’ve seen
@enlightenedbanana
Жыл бұрын
I like how all the most popular aussie youtubers are also the “most sane”
@alex.g7317
Жыл бұрын
low bar tbh
@EEEEEEEE
Жыл бұрын
E
@zach1425
Жыл бұрын
@@enlightenedbanana it's like being the most lively corpse in the morgue
@Tenems941
Жыл бұрын
@@enlightenedbanana I think "How to Basic" is Australian. I know Max and Chad from "Cold Ones" are so maybe that levels the balance a little.
He really did have the second video ready. So proud Mr. Bullet.😊 With two videos in a week, I look forward to the next video in 2024.
@judex2559
Жыл бұрын
@SiZzyVFX that’s being optimistic
@TheBuildMiner210
Жыл бұрын
I was so confused when the 2nd part came out earlier than 2 years later
@Inveist
Жыл бұрын
Think you misspelled it's 2034
@wify0241
Жыл бұрын
Being a bit hopeful there aren’t we?
@wify0241
Жыл бұрын
@@Inveist 3034*
Started watching your videos a few years ago. Finished my degree in Game Programming last year. What you do is absolutely insane, and I don't fault you one bit for 2 - 4 videos a year. Having said all that... I need to see these boys walking forward, and you must absolutely bring back the death laser. EDIT: I made you a death laser and sent you a link to the repo.... soooo, you know, part three would be cool.
@strykerwaller3784
Жыл бұрын
I admire you being the change you want to see in the world
@cheman9907
9 ай бұрын
@@strykerwaller3784me too. Don’t stop that
@Wall-knight
6 ай бұрын
23:20
@dtsprogramming
6 ай бұрын
Laser Wall: kzread.infocYxzTAuTYWM?si=M2atFnIMKVcFrUXi
I guess the models' feet are rigid, but the movement of toes plays an important role when walking and running, so adding another joint behind the toes might help a lot for AI to learn walking. (especially not backwards :) Additionally, I think instead of killing them when they fall, killing them only when their head touch the ground and giving serious penalty points for touching their body parts (may differ for front and back also) other than bottom of the feet, also giving less penalty points for hands may force them to learn getting up when they fall. This approach may make them learn to stand up properly and walk. Moreover, if you give them slight penalty points for touching the bottom of their feet than they may learn to jump towards the target which may lead them to learn to run even before walking :D All these might lead them learn to run on all fours at first, but they will learn to stand up eventually if the penalty and reward points are balanced well. If speed is rewarded more, then they will stay on all fours, but in this case if the height of the head is penaltied or rewarded, then standing on feet will be flourished. Maybe they can run like Tom Cruise some day :D Just speaking my mind, you are the expert :)
@xjerrylee22x
Жыл бұрын
You are absolutely right, be he will avoid doing that kind of work? And instead waste his time with insufficient methodologies :)
@appledognugget2267
3 ай бұрын
I’m really sorry but you lost me at *TOES*
Seeing the time lapses of the AI in their individual cubes feels disturbingly dystopian
@engineerxero7767
Жыл бұрын
Reminds me of the Truman Show
@Dolat1984
Жыл бұрын
What's with the santa account that I assume is a bot given the obvious copy paste message all of them have
@stupit467
Жыл бұрын
@@Dolat1984 AI learned to scam
@Dolat1984
Жыл бұрын
@@stupit467 dear god AI is taking scammers jobs too hahaha
@allesman
Жыл бұрын
@@stupit467 the next logical step
AI finding a loophole and looking backwards instead of learning how to walk forward is oddly relatable
@_charademon_
Жыл бұрын
Vitecplay - russian youtuber played the evolution style game, where he wanted to make a rolling circle, but it just kept collapsing on its own volution and then proceed to jump forward.
@theendersmirk5851
Жыл бұрын
In fairness, I'm somewhere around 80% certain they're only doing that because CB accidentally made the back side heavier than the front, since they would, no matter what, always fall on their back when with humans that's more even between forwards and back, and walking is essentially falling forwards while continually catching yourself. Since they automatically fall backwards, they also learned to walk backwards.
@Red-Tower
Жыл бұрын
@@theendersmirk5851 yeah I was kinda thinking about that. To be fair, I think it started off falling any both directions, but somehow early on it found it could get closer to the goal by falling backwards, so it became intentional by the AI. The funny thing is, I think even if he had the "look at the target" parameter in place from the start, it still probably would have fallen backwards, assuming the model could tilt its head up/back enough to see the target from the ground. Amusingly, the "point your d!ck at the target" aka have the pelvis face the objective I think would have been the best option for getting it to walk forward, since it has the least freedom of rotation separate from the rest of the body, it would have basically forced it into a forward walk. (Although if that was the case before he forced it to stay on it's feet, it probably would have started humping the air...)
@ssholum
Жыл бұрын
@@Red-Tower Looking at the feet, the ankle joint might also be part of the cause for falling backwards all the time. Either it got reinforced to always go into plantar flexion early, or it doesn't have the joint mobility for dorsiflexion; either of those would encourage it to fall backwards, which would make the backwards walk the closer solution.
@EEEEEEEE
Жыл бұрын
E
They did pretty well considering they had no inner ear, spine or directional awareness related to their face, a working spine and the world. Something to give them priority for facing forward without twisting the neck, something to favour keeping the head relatively level with the horizon and something to favour holding a more upright position.
Accidentally created a JoJo pose generator in the process of trying to get a hot man to walk.
could milk a third video from this making them walk straight
@ConstantlyDamaged
Жыл бұрын
Oof. I mean, true, but oof.
@justsomeguy5628
Жыл бұрын
Or make it animals walking on 4 legs
@Ceafto2007
Жыл бұрын
Girl they were sucking each other's dick within 2 hours of being created they would never be able to do something straight
@skippykay599
Жыл бұрын
That’s a big ask, does anything in this video seem straight to you?
@armoule8596
Жыл бұрын
To make them walk straight, he would need to articulate their feet and toes, essentially adding 2 beans per leg (on for foot and one for toes) and the beauties will run for sure
Part three? We still need to see them walk like humans.
@knownas2017
Жыл бұрын
Wait, you don't walk like this? wtf
@ludvigjansson5790
Жыл бұрын
What if they could actually run towards you. That woundn't be scary at all.
@juicetin6425
Жыл бұрын
@@knownas2017 nah bruh we fly 💀
@lordyoofy5529
Жыл бұрын
@@juicetin6425 Bro you don't conjure a bubble of blood and other fluids to swim along the ground in?
@outsider344
Жыл бұрын
These aren't ever going to walk like humans. The human gait is caused by loads of factors that aren't being simulated here. Like specific joint structures
Makes ai walk and the first thing he does with it is make them do the fitnessgram pacer test
@xander9488
Жыл бұрын
Ok who the mofo deleting all the comments telling telegram Evan bot to *shut*
this is genuinely one of the funniest videos I have seen in a loooong time, my throat hurts from laughing so hard. You're legendary CodeBullet.
It feels strange to have 2 codebullet videos to watch in the span of 3 years
@psgamer-il2pt
Жыл бұрын
10*
@HiddenWindshield
Жыл бұрын
@@Diathan Don't reply to bots (even the "ironic" ones). It just makes them look more legit to the KZread algorithm, and leaves a link to their channel in your post. Just report and move on.
@EEEEEEEE
Жыл бұрын
E
@yourlocalgay1452
Жыл бұрын
@@HiddenWindshield not a bot hahahah
"we're gonna have to force them to stand up" yeah because they were gonna evolve into crabs if left unchecked
@AkoSolius
Жыл бұрын
Because in this universe everything evolves into crabs eventually
"You have lost suck privileges" - Code Bullet
@user-me3te8ht4s
3 ай бұрын
that killed me 😭😭😭😭😭
Omg, a vr horror rougelike where the ai monsters progressively get better at chasing you
I honestly thought he would just never do the rest. Finishing a project is very out of style, you go Evan!
@ZoltarDeathNnja
Жыл бұрын
But he didn't finish. He gave up before getting them to walk forward or stand up after falling!
@brunogonzalez7453
Жыл бұрын
@@ZoltarDeathNnja bullet found a way of turning into a homoerotic fantasy AGAIN
@ZoltarDeathNnja
Жыл бұрын
@@brunogonzalez7453 Did he find a way to do it, or did they AI force it upon us?
@vrcookingsimulator5458
Жыл бұрын
@@ZoltarDeathNnja Lol
@Red-Tower
Жыл бұрын
@@ZoltarDeathNnja If so, I'm a big fan of this AI
Part 3: Ai learns to run Part 4: Ai learns to hug Part 5: Ai learns love Part 6: I married my AI Part 7: WE GOT KIDS!
@urmum8540
Жыл бұрын
Part 8: Help
@blacklight683
Жыл бұрын
@@urmum8540 part8:the divorce
@audionewpaper1
Жыл бұрын
Part 9: depression
@RAFMnBgaming
Жыл бұрын
@@audionewpaper1 Part 10: What was the AI cooking?
@EEEEEEEE
Жыл бұрын
E
9:12 “AI Learns to Eat Ass” video when?
3:26, Guy's almost pulled a DIO off
Honestly love the line graph bit
@snehsrivastava7107
Жыл бұрын
👍
@mukeshrathod6335
Жыл бұрын
Best
@savanchavan5313
Жыл бұрын
Nice
@philrod1
Жыл бұрын
Should have been left to right, but still nice 👍
@muneermirza4301
Жыл бұрын
Best
Hi Code Bullet, I think the backwards issue is related to the starting position. The T pose is just a bit back heavy, so they naturally fall back and continue there movement in that direction. If you where to start them with their arms forward, they would likely learn to walk in that direction.
@Jay7707
Жыл бұрын
There’s a lot of smart people on the Internet and this is one of them.
@alasdairsinclair916
Жыл бұрын
So the problem is that their booty is too _thicc_
@pixelblaze8284
Жыл бұрын
Honestly there's just a lot of issues to address. Like part of why we walk on two legs and forward is energy efficiency, our toes and foot flexibility, needing to see where we're going, etc. So you would just need a lot more inputs to try to make it happen in a realistic way that isn't just forced like he tried to do
@minamagdy4126
Жыл бұрын
I believe it has more to do with the AI wanting to use the hips as little as possible, so it prefers a backward gait due to the fact that knees can't bend forward. EDIT: more like the knees as little as possible, but exploiting a nonzero knee angle for stability
@Xeroisawesome
Жыл бұрын
@@minamagdy4126 Well that's related to how the abdomen was simplified so much that the AI had much fewer option for maintaining it's balance than a person would. There were just a lot of problems relating this model to human movement, I doubt I could list them all. With that said, it was uncannily close in some ways despite those shortcomings.
24:17 Me and the boys walkin'
These videos are beautiful. Please never stop being chaotic Code.
I think the proprioception idea is a good one, but I don't think its enough alone. In us humans, that sense is combined with the inner ear (which conveys a sense or roll, pitch and yaw) and vision (which provides directional targeting). So along with a sense of proprioception, you need to simulate an inner ear and a "cone of vision." Alas, you would have to train AIs to this task incrementally though. For example - you'd have to start training vision first (where it looks for a target in its cone of vision, and if it's not there, it turns its head/body until it finds it). The inner ear should already be working for this part of the training (so a sense of perceived direction and range emerges). And once it's learned to look at a target, then you can then try to train them to walk. As long as they learn to rotate themselves to look at the target first - they should walk forwards towards it. Moral of the story? They should look before they leap. :D
@StevenIngram
Жыл бұрын
(To be clear by what I mean by a cone of vision... it's basically an invisible non-clipping cone that extends from where the eyes would be that has the same field of vision and range as human vision. For it to register anything as "seen" it must be inside the cone).
@themonkeyman2547
Жыл бұрын
Another important detail the AI is ignoring is effort. Walking upright in the human style is extremely efficient. Walking bent over backwards with arms flailing in the air like the AI did is extremely difficult. If they were made to minimize energy use, I think the results would improve
@EEEEEEEE
Жыл бұрын
E
@101k_with_no_video
Жыл бұрын
or fall to the ground like a ####### loser
@Betheno
Жыл бұрын
this is the guy code bullet is scared of
Fellow fans of Code Bullet: it doesn’t matter if you watched the previous video before this one.
@flabort
Жыл бұрын
Yeah, but I think this one hits different if you did. I personally think it was worth it.
@imperialphoenix1229
Жыл бұрын
It was totally worth watching but like.... Yeah you really don't need it for context
@tapferer1kater34
Жыл бұрын
Honestly, I didn’t like the first video very much, this video is much better
@Red-Tower
Жыл бұрын
Well, if you're a fan of Code Bullet, it helps him out a lot if you watch both videos!
@forkleftism9692
Жыл бұрын
If you didn't watch the first one, how would you know humans are just beans?
The fact that in one of the vr experiences, they were... Doing adult things... shows that your ai is more powerful then ChatGPT
Am I the only one that the audio is way ahead of the video?
19:14 I love that they're so committed to the backwards thing that they hit the target, then _turn around so that they can still be backwards_ before heading to the next one.
@Kerostasis
Жыл бұрын
They never learned how to walk forwards. That was probably the same issue with the turning necks thing: he added the "face your target" reward to a bot that already only knew how to walk backwards, so rather than re-learn an entirely new skill, they just turned their heads as part of the existing skill.
This made me realize why crabs keep independently evolving
These two videos might be the funniest videos you have ever made. Cannot stop laughing every time you get submerged in all these player models in VR
10:50 I love this guy’s humor and comedic timing. I can’t believe I’m saying this for the ad segment.
It is honestly amazing that CB managed to get them to walk without falling over. I expected the usual AI exploits physics engine to happen and the guys to vibrate across the floor at light speed instead
@kivylius
Жыл бұрын
well the several constrain prevent that from happening.
@nikkiofthevalley
Жыл бұрын
@@kivylius Plus he's using a much more popular physics engine (PhysX, Unity's physics engine), so most of the easy to trigger exploits are patched.
I love how they immediately find a way to exploit the system to avoid walking forwards
By Golly, not only the themes you chose for your videos and your skill to actually do them and show them are more than on point, but also your editing and silly jokes are hilarious, I cried from laughter more than once.
23:40 How tf did it take him so long to realize
I think the main 2 reasons for the AI behaving the way it does is likely because: a) friction is not quite correct making it not actually use their legs to push forward but their lean over weight to pull them. b) I assume every bone is the same weight and every joint the same strength which causes strange priorities. Oh also there could be a added reward to keep the center of gravity beneath the head within a range that might also help
@besknighter
Жыл бұрын
Agreed. Also, there are a lot more things that could be done to improve it. For example: calculating the energy expenditure and rewarding the most economical ones; rewarding those that the time of arrival is closest to a specific set goal (having the remaining time as an input together with the distance to target will help) will also make them learn different kinds of gaits for different desired speeds. Of course, changing how much reward each variable gives will drastically change the outcome.
@somedude4487
Жыл бұрын
Technically we also use our weight to walk, so the friction is fine, the AI just found a local maximum to attach itself to
@TheNeonLynx
Жыл бұрын
@@somedude4487 Hmm how to describe this. Irl friction is a force that opposes movement. Pushing against it will let you use it to move i to the opposite direction of where friction goes. (Kind of think how high jumping with a stick works they use the elasticity of the stick and the opposing friction to propell themselves upward) However in this game friction presumably works closer to how magnets work. A magnet wont let you push against itself since it always pulls you back. A magnet will never push on you so you cannot use it to push yourself forward. So the Ai can only pull its feet off the groumd not push its body off the ground and thid movement is the result.
@duchuynhvuong1733
Жыл бұрын
ok
@Middleseed
Жыл бұрын
@Yara Yo The Chinese/Japanese (I don’t know either give me a break) bots have infected the English comment threads!
he finally mastered the art of making the audience believe he is dead and then boom he is back
@arfb01
Жыл бұрын
Are we sure he isn’t a zombie
@theonly6blake911
Жыл бұрын
@@arfb01 Now that you mentioned it, his face does look awfully green...
@EEEEEEEE
Жыл бұрын
E
@swagmaster4396
Жыл бұрын
@@EEEEEEEEe
Now if only we could get Enigma Part 2
i love these ai learns to walk videos cant wait for what you do next
At 0 hours of training, the AI behaves remarkably like a newborn infant. The movements are random because it has yet to develop "awareness" of its limbs and how to use them. I just thought it was a really interesting comparison.
@yahiaaymankamaly3518
Жыл бұрын
If my baby started doing this im taking it to the hospital
@dieSpinnt
Жыл бұрын
Yeah, computer science can be surprisingly childish. Which is strangely not a derogatory term, here. **g**
@keysersoju9823
Жыл бұрын
Imagine if he just left the crawling AI to learn for generations, I wonder if any of them would've evolved to walking like how a human learn to crawl first then learns to walk.
@rockyroadmagic4152
Жыл бұрын
@@keysersoju9823 I doubt it. Newborns move on to walking eventually because crawling is more tiring, and hurts the hands and knees after a while, and also probably because they see everybody else walking. Without the punishment for parts other than feet touching the ground to simulate the discomfort of the first two reasons, it would not have any reason to stop crawling
@visyix2718
Жыл бұрын
So from the whole beginning I was just an AI
It’s amazing seeing the AI use the arms to maintain balance
@EEEEEEEE
Жыл бұрын
E
3:55 FAIRY ODD PARENTS😂😂😂
This two-part video contains an impressive amount of getting sidetracked. Hilarious, I might add. Watching AI fail at walking is an amazing and comforting sight. Laughing at real people falling feels bad because they get hurt, but watching an AI-controlled puppet fall in virtual 3D seems harmless
the fact that codebullet got a bunch of buff men to moonwalk at him chode-first is truly the peak of AI
The waiting for this series was worth it ngl Codebullet always delivers
@raptorprime1831
Жыл бұрын
after a year.
@ChuckSploder
Жыл бұрын
except for walking forwards
@Ferrari255GTO
Жыл бұрын
This is the funniest shit i've sen in a while ngl
“I don’t know why they’re walking backwards” *spawns them facing away from the target
This is by far the best and funniest codebullet video to date!
Create a time limit on how long it takes them to reach the target so they have to learn to sprint
@Krell356
Жыл бұрын
In theory they should already be getting rewarded more frequently based on the distance closing so a timer shouldn't be necessary.
@Dark-Stryder
Жыл бұрын
@@Krell356 it would speed up the process tho wouldn't it?
@Krell356
Жыл бұрын
@@Dark-Stryder Not really. If you move half way to the target in the same time another version moves 75% of the way. The further one would have been rewarded more points. So the one that got further is less time is already being reqarded better.
@MythicTF2
Жыл бұрын
@@Krell356 I'm not an AI specialist but, if theres multiple targets and no cap on the score said AI could get in a single generation, theoretically a timer would still make it go faster. It's probably not necessary for this and would probably lead to the AI just discovering something unintentional like leaping towards the target as the timer is about to run out. Without a timer though, the AI that moves 75% of the way to the target in the same time as the 50% of way would still be rewarded more points but, a target that moves 50% of the way in 3 minutes vs 50% of the way in 3 seconds is also a huge gap where a timer would improve it, and in turn teach it to go faster.
@Gelo2000origami
Жыл бұрын
I think that yes, this could be a weight that can be conditionally added into the model once the AI model manages to reach goal 1
it’s like watching infants learn, just like babies the AI only seems to know how to *push* at first lol. probably why it’s more comfortable moving backwards
@SilverWolf_-cj4qn
Жыл бұрын
I think the balance is off on the ai models. I think there's more "weight" at the back of the model so they end up stumbling backwards because they can't fall forward
@abeke5523
Жыл бұрын
@@SilverWolf_-cj4qn cuz of all that cake
@blueninja012
Жыл бұрын
@Rahaf Ahmed THE BOTS ARE LEARNING NEW LANGUAGES GOD HELP US ALL
Mate, this may have been a better comment on your last video but I didn't think of it until now... You going off of any form of script do your own thing and entertain while talking about a concept or idea that I'm interested in, is a breath of fresh air in a KZread world full of video essays that clearly have to stick strictly to script. In the words of the great Code Bullet himself... I do what the fuck i want. Let me smash that like button as if it's the chosen one.
This is the most unhinged video you've posted yet, I'm still dying
i wanna see a part 3 where they walk like you know humans
@s-a-g-e
Жыл бұрын
Humans... CAN walk like that... technically
@Mike-wu5ef
Жыл бұрын
what do you mean? how do YOU walk?
@pickupthatcan9903
Жыл бұрын
Same
@OKayD3N
Жыл бұрын
You don’t walk with your shoulder blades?
@ilyaalexandrovich917
Жыл бұрын
@@OKayD3N when he sped it up it looked like a cockroach race
10:18 He says he's connecting to habitable country while showing france truly the funniest person on the internet
@axeldasilva8060
Жыл бұрын
I don't get it
@Red-Tower
Жыл бұрын
I mean, compared to Australia? As funny as "huhuhuh french people silly dumb cowards oui oui" is, Australia do be fucking savage.
@kal-muzel875
Жыл бұрын
@@axeldasilva8060 me neither
@TlalocTemporal
Жыл бұрын
@@axeldasilva8060 -- Australia is uninhabitable due to the temperatures and the spiders and a million other nasties. France is uninhabitable due to the French.
@kinggenderman1874
Жыл бұрын
fr*nce 🤮🤢🤢
Merry X-mas Code Bullet and everyone else. Nice to see u still making videos. :)
The "laying down walk" finally made me understand why things tend to evolve into crabs, great work!
Honestly love the line graph bit. It also totally would work. Hours Trained x Walkability.
So, we actually have neurons in our spines that generate cyclic rhythm for walking. Look up Central Pattern Generator. It's pretty cool to generate cyclic impulses out of just a bunch of neurons connected in a loop (albeit, that obviously does not fit the layers of neurons models you can find in most NN packages...). Second important thing in walking, is that proprioception is used for reflex acquisition. Eg. certain angles of certain joints trigger the next movement in the sequence. Which for "AI simplicity" can possibly be done as a feedback/reset input on some CPGs.
@clorax1357
Жыл бұрын
^^^^Genius. I think rewarding them for having an average floor touches/second over a given amount of time (or whole run) would be a good way to implement this slowly, avoiding incessant steps. Another way you could diversify the AI’s ability would be to set the cyclic rhythm goal at a random value within a reasonable range.
@johnalogue9832
Жыл бұрын
It turns out walking is hard to replicate by wiggling joints at random until you get closer to a target point.
@revimfadli4666
Жыл бұрын
Joint angle proprioception determining the next timestep's angle outputs reminds me of ohmganesha's kinesthetic worms
@YoAndyZou
Жыл бұрын
I saw a NN video the other day in which they simply included an oscillator as one of the inputs; perhaps giving the AI output control over the frequency of those oscillations might be a simple way for it to feed itself information... Just a handful of sine waves, etc? I get that with enough information it might be able to synthesize cyclical motion based on its current state, but wondering how many shortcuts/better architecture there is for locomotion activities.
@halal_gaming2010
Ай бұрын
biologist entered the chat
That 3:43 startled me, but super hilarious, I'm literally LMAOing. Good stuff.
Well, we will never see him again, he learned how to walk away from us thanks to AI
@Red-Tower
Жыл бұрын
Made himself AI friends so he doesn't need us anymore 😭
@Ferrari255GTO
Жыл бұрын
@@Red-Tower no, he'll be back, he still has to eat and without youtube, he is doomed
@EEEEEEEE
Жыл бұрын
E
@theblah4341
Жыл бұрын
@@Ferrari255GTO He can eat the AI
@Ferrari255GTO
Жыл бұрын
@@EEEEEEEE E
I think that the sight of several men walking towards Bullet in the most unhuman way possible was worth all the effort he put into this.
Yours are the only ad Segways I don't skip too lol.
Watching this video makes me glad I'm not a coder but also this is the most entertaining video I have watched in a long time
Pretty sure the reason they walked backwards is that they fell backwards in the default position, causing them to take a step backwards to prevent falling over. If you would just have tilted them forwards a little at the start, the first step would have been forwards and they would have continued walking forward. The backwards thing was funnier tho soI can see why you didn't try too long and hard to fix it.
@buckykattnj
Жыл бұрын
Interesting... I thought that the problem was that the feet seem to be modeled as one inflexible object... and obviously, feet don't work that way. I thought that at least making the feet hinge at the toes would avoid the backwards, tippy-toed approach the AI is using. Or is could be a little of both of our ideas together might finally get hem to walk forward.
@Ferrari255GTO
Жыл бұрын
@@buckykattnj nah, the real fix is to put a clone with a machete behind them that already knows how to walk.
@Terrain239
Жыл бұрын
Also the first part (without touching penalty) could be interesting with forward falling -- sort of animal 4-leg walk
@xxlvulkann6743
Жыл бұрын
Maybe randomizing the falling direction as well as adding a vestibular sense would allow for a more robust locomotive system.
the long awaited sequel finally arrives
@MW_Green
Жыл бұрын
It been 4 days but yep
“I’m not a scientist” is literally a computer scientist
i havent laughed to a youtube video in forever. this is gold.
Give them a reward for moving in the direction of their front, a reward for keeping their shoulder height up (but penalized for shrugging XD), and a penalty that increases the longer their toes are on the ground without their heels also touching the ground, and make them have a vision cone for finding the target they have to move to :D
@Thk10188965
Жыл бұрын
perhaps the toe stance discouragement could begin if there is 1 to 3 seconds of toe touch without a heel touch (possibly also the reverse to discourage heel walking too) making the foot a little rounded in the back and with a flexible front section (toes) might also help to better match real feet. as for rewarding standing, reward head above shoulders, shoulders above torso, torso above legs, upper arm above lower arm, upper leg above lower leg, lower leg above foot (probably by failure hurting score, rather than success helping it much)
@goldfndr
Жыл бұрын
No need for a reward for moving in the direction of their front. Instead, penalize exponentially for head pivoting away from neutral.
@H4PPY_23
Жыл бұрын
What about friction? Wouldn't it be easier?
@elinhulldin5926
Жыл бұрын
@@goldfndr Yes, that worked for me. I tried to walk like them and my neck started hurting after 5 seconds, so I turned around.
@Xboxiscrunchy
Жыл бұрын
Your comment made me realize this is pretty much exactly what pain does for humans. Maybe penalize the AI slightly any time it overextends or over taxes its joints? Cause that shit would hurt if a human tried it.
I wonder what would have happened if the “touching the floor” punishment were a reduction in score instead of immediate failure…
@jaydnrae9829
Жыл бұрын
Or if instead of a penalty, it was a reward? I want to see how fast they could worm 🪱.
@poop9267
Жыл бұрын
Rolling around at the speed of sound
I love the editing effort
Nice video as always! I think it would be really interesting to see how they would walk if you added "work" to their properties. So that they are trying tp walk with doing as little work as possible in relation to gravity and muscle strength. That way they would put their arms down and maybe try to stand straighter
While I buy a dakimakura for my crippling loneliness, Code Bullet makes his own AI so he has friends which will follow him. Now that's some determination!
You should teach ai to code and make an endless loop.
@MultipleC9
Жыл бұрын
teaching an A.I. to code would be very interesting but may end up creating skynet lol
@krishanSharma.69.69f
Жыл бұрын
@@MultipleC9 that is exactly what most humans are trying to make ... a recursive self improving AI.
@samwilde8311
Жыл бұрын
@@krishanSharma.69.69f didn't google successfully create an AI that created a new method for training AI? Edit: Because no one believes me I did some more research. The AI I'm thinking of is called AutoML, it uses an AI model built by Google to produce AI models faster and more accurately than those produced by human training.
@pablovirus
Жыл бұрын
@@samwilde8311 nah, that's media bullshit
@knownas2017
Жыл бұрын
There already is an ai that can code btw.
I haven't cried laughing so hard in ages. Thank you CB ❤️🤣
so upset you only upload like 6 videos a year, every time i watch these i have to pause cus im laughing so hard. good shit man
23:24 "My God that is hard to look at". No pun intended. Then proceeds to turn the camera back and look again.
16:12 And in the end, it didn't even matter...
@Tha-mountain
Жыл бұрын
HE TRIED SO HARD AND GOT SO FAR
24:29 Caught me all the way off guard while I was drinking. Almost ruined my keyboard lmao
okay but the jojo posing bit is actually the hardest I've laughed at a youtube video in a long time
They call him code bullet because he's slow (like a bullet)
@gabrielp-l9905
Жыл бұрын
yes classic bullet behaviour
Actually if he could get this working where they walk forward then change the avatar to a zombie then give yourself a shotgun I think he might have the start of a epic zombie game
@garrettcooper58
Жыл бұрын
That’s exactly what I was thinking. It could be an insane vr zombie game
@nezzled
Жыл бұрын
could be an interesting concept. A wave based shooter where the enemies gradually get smarter as the game progresses.
The good thing about your upload schedule is that since you upload every other blue moon, i can binge your whole channel when you actually happen to upload
I’m watching this at 3am and I have a 10h shift at 6am Thank you for the dark bg
2 videos in 1 year? we must have been nice this year to deserve this much content
17:22 this is how nature intended humans to walk
i legit laughed out loud at the touch target shotgun scene. Goddamnit that was a good one
I haven't watched code bullet in like 2 years. Still amazing
I liked the video up until the point you made their necks twist 180 degrees to circumvent the back-facing walking, I would've loved to see them actually walking, I think the video was really funny and wish to watch part 3, with more accurate posture and speed, maybe less disjoined necks
@traywor1615
Жыл бұрын
agreed, it's a shame he didn't added that chest and d**k reward.
@bungsbodulus
Жыл бұрын
Yea same
@matroqueta6825
Жыл бұрын
I agree, the neck thing was pretty weak
@Big_Con
Жыл бұрын
I agree as well
3:21 That flying dab tho!
At the beginning of the video when the guy was broken and it was just hopping around and it just expands. I need more of it. I like it when stuff doesn't work, especially when it's funny
I have never been so hyped for a part 2 video to drop. But I wish you had programmed them to actually walk normally.
I find it interesting how similar this AI learns to walk as a baby does. Start off just randomly flailing with no real sense of what they’re doing, then slowly work out how to crawl towards an objective. It’s shockingly similar to real living things learning to walk, even considering all the jank
@__u__9464
Жыл бұрын
That's because ai literally works as our brains do
@-TheBugLord
Жыл бұрын
@@__u__9464 It actually doesn't. That's a common misconception though.
@jtcoding6422
Жыл бұрын
@@-TheBugLord it’s like the same concept, neural networks r based off brains
@__u__9464
Жыл бұрын
@@-TheBugLord yes it does. It aims to recreate the function of a brain
@-TheBugLord
Жыл бұрын
@@jtcoding6422 Yes. Based off, but does not work as our brains do. There are many differences. And, neuroscience isn't far enough to even determine how the brain actually works. But here's a simple example to show the differences. Neurons in neural networks are not like brain neurons at all. A brain's neuron is either on or off. A neuron in a neural network, however, can be on from any range between 0 an 1. You can have a 0.5 activated neuron in a neural network. Yes, it is true, neural networks are based on how the brain works. But to say they work as the brain does is a misconception and false. And our scientific knowledge is not far enough to even determine something like that yet.
4:55 that cursed Section went on for far too long. It was perfect. 10/10 Content :)
Two videos back to back? I can't believe it lol. I'll be eagerly waiting for the next dose of Code Bullet in another 6 months haha. The shadow made the "humans" so much scarier. The elongated limbs, stretched neck, and dislocated joints were beautifully awful looking.
I got a better laugh for 26 minutes watching this video than I did in this year Thank you so much bro, what a quality content XD