world's best ai vs geoguessr pro

Поділитися
Вставка
  • Опубліковано 19 гру 2024

КОМЕНТАРІ • 2 тис.

  • @anandmaha1
    @anandmaha1 Рік тому +17457

    pressuring an AI model to push out a prediction by inputting your answer quickly is the funniest shit I have ever heard.

    • @LeoAr37
      @LeoAr37 Рік тому +433

      I mean if the AI needed more time to upload and make the inference then yes it would work, but yeah not in the "pressure" way lol

    • @aureus79
      @aureus79 Рік тому +443

      Thats how we used to beat the cheating extension people used to use a couple years back. It could see the data behind the pic and 5k it but it needed like 20 seconds, so if u guess within the first 15 it just didnt guess lol

    • @gabrielamaral978
      @gabrielamaral978 Рік тому +24

      Is just limiting the ai processing time.

    • @GoalHubYouTube
      @GoalHubYouTube Рік тому

      @@gabrielamaral978 18 sec ago

    • @wtf17727
      @wtf17727 Рік тому +37

      That could be a way.
      Large AI models are pretty slow and need time.
      Just look at how long Bing sometimes takes to answer and they have a lot more power than some students I would guess.

  • @matthewsatthewsssss4115
    @matthewsatthewsssss4115 Рік тому +11822

    1997: Deep blue beats Garry Kasparov at chess
    2023: Stanford AI beats Rainbolt at geoguessr

    • @3446
      @3446 Рік тому +222

      It was a 2 month long project. Rainbolt took years.

    • @AnindyaMahajan
      @AnindyaMahajan Рік тому +815

      ​@@3446 That 2 month long project relies on the progress made by thousands of super smart scientists in the field of AI spending their lifetimes in research over the last century.

    • @joshwhitley8969
      @joshwhitley8969 Рік тому +38

      Not even a comparison. Gary chess way more impressive.

    • @ashscott6068
      @ashscott6068 Рік тому +199

      ​@@joshwhitley8969 Huh? No, a chess computer is extremely simple by comparson. It's literally just analysing every single possibility, even the really stupid moves. Chess has very few rules, and a single clear objective, and can easily be reduced to a few simple instructions. It's a very easy thing for a machine to be good at: Just brute-forcing all the possibilities and possible responses to responses to responses, down to a given depth.

    • @orangeover5539
      @orangeover5539 Рік тому +75

      ​@@ashscott6068no just no
      Until today no one has built a bot that knows every position in chess
      There is more position than atoms in earth you couldn't multiply it because the knight moves different the bishop does different pawn does different rook does different
      The highest bot today in chess in stockfish 16 the newest realease just beating stockfish 15

  • @istiaan
    @istiaan Рік тому +12005

    No way Tom Holland and Shawn Mendes collabed to make an AI to curb stomp your ass in Geoguessr

    • @gameplayz5847
      @gameplayz5847 Рік тому +52

      fr 😍😍

    • @eksen7221
      @eksen7221 Рік тому +115

      Mf this is so funny😂

    • @dacallp
      @dacallp Рік тому +10

      😂

    • @alimahmoud6966
      @alimahmoud6966 Рік тому +56

      tom holland from ohio

    • @hejalll
      @hejalll Рік тому +56

      The tom holland-lookin guy has such a look, I love it. He looks like someone straight out of a movie.

  • @Askejm
    @Askejm Рік тому +1068

    for anyone wondering, the paper is called "Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalization"

    • @Risyn1
      @Risyn1 Рік тому +10

      thanks bro

    • @mip4422
      @mip4422 5 місяців тому +17

      what is "learning generalized zero-shot learners" even supposed to mean?

    • @deadshot_ed1ts
      @deadshot_ed1ts 5 місяців тому +8

      I think they made that up just to make it sound cool😂

    • @Askejm
      @Askejm 5 місяців тому +73

      @@mip4422 the zero shot means it guesses things it has never seen before without examples and the open domain shit means it can guess the location of anywhere in the world, not limited to specific places

    • @linminhtoo
      @linminhtoo 3 місяці тому +4

      ​@@deadshot_ed1tsit's genuine

  • @_Atlas.
    @_Atlas. Рік тому +2437

    I've never seen this guy before but the fact that he could almost beat the AI trained on so many pictures is absolutely insane.

    • @Nova0Rock
      @Nova0Rock Рік тому +68

      At this point in time, he has probably seen more ;)

    • @Gabriel-hm7vv
      @Gabriel-hm7vv Рік тому +91

      @@Nova0Rock AIs can play more games of chess against itself than a grandmaster can play against any oponent, really, during a lifetime. I don't think so, if this AI can be trained using images, it will use basically every image available.

    • @skull1161
      @skull1161 Рік тому +90

      @@Nova0Rock He has been using geoguesser longer but an AI has basically no concept of time the way we do, they could train so much more in a couple minutes than we ever could in years. They said they showed the AI 250,000 images to train. There's no way rainbolt has seen over 250,000

    • @amjan
      @amjan Рік тому +4

      He has actually beaten AI before.

    • @olasdorosdiliusimilius2174
      @olasdorosdiliusimilius2174 Рік тому +2

      The game was rigged against the AI there lmao

  • @antimatter4733
    @antimatter4733 Рік тому +8371

    AI really just said "I recognise that dead insect on the camera"

  • @GeographyChallenges
    @GeographyChallenges Рік тому +11236

    So much to learn from analysing what the AI is actually looking at in the image

    • @rumilb
      @rumilb Рік тому +178

      meta players smh /s

    • @worldalternate
      @worldalternate Рік тому +353

      Definitely gonna be getting a a bunch of new dirt on camera metas

    • @_Cant
      @_Cant Рік тому +69

      The ai actually just scanning the place thats it 💀

    • @Jonassoe
      @Jonassoe Рік тому +56

      You could just train an AI by making it play a billion times and do basic image recognition. You don't even need an AI for that, just save every image you see and map each of them to a set of coordinates.

    • @antimatter2417
      @antimatter2417 Рік тому

      ​@@Jonassoe and when new coverage comes out you're fucked

  • @user-svqmbiv
    @user-svqmbiv Рік тому +5963

    Dang, geoguessr is about to have engine prep just like chess

    • @h20dancing18
      @h20dancing18 Рік тому +294

      That’s what I was thinking. Pigeon is the stock fish of geoguesser

    • @gingeral253
      @gingeral253 Рік тому +208

      This is actually crazy. It’s scary if malicious people get this tech to track people.

    • @soyanshumohapatra
      @soyanshumohapatra Рік тому +10

      Ohh wow! I never thought of that😮

    • @BenjusJamentus
      @BenjusJamentus Рік тому +51

      I suppose it's a bit different, because every round in geoguessr has a 100% correct answer, whereas in chess, the best moves are calculated by the engine. It would be comparable if you wouldn't get the solution to a round in geoguessr and had to verify your guess manually

    • @iZelmon
      @iZelmon Рік тому +60

      @@gingeral253 Shit you got a point, this might seems actualy malicious tool hidden behind harmless fun.

  • @Filbie
    @Filbie Рік тому +715

    It’s truly impressive that it takes a specially trained AI to beat this guy

    • @starxdreamz.
      @starxdreamz. 4 місяці тому +14

      How do you think ai is made at all. You have to train it

    • @_Yuki.v.
      @_Yuki.v. Місяць тому +6

      @@starxdreamz. I think they meant that it was specifically made for that purpose

  • @fotheon-9955
    @fotheon-9955 Рік тому +97

    The smudge thing makes me wonder if the camera can pick up on stuff like a region having 2% less bright photos than another similar region because it's an hour later in the day. If it hyperfocuses on such inhuman metas it should be pretty bad at transfering the skill to photos that imitate the google street car but are not original geoguessr footage.

  • @MrJobocan
    @MrJobocan Рік тому +2875

    The AI got so much better since the last AI video, this is really impressive. Good job to those guys!

    • @soyanshumohapatra
      @soyanshumohapatra Рік тому +1

      Yo

    • @rubenverster250
      @rubenverster250 Рік тому +1

      and how much better did this guy get ;D

    • @gavinjenkins899
      @gavinjenkins899 Рік тому +7

      Main advantage probably has very little to do with the AI and more what they were talking about with sort of pretraining it by feeding it politically/geographically relevant cells that they picked out manually

    • @yuusha16
      @yuusha16 3 дні тому

      ​@@gavinjenkins899That's how most child prodigies are made.

  • @nathanholmes4942
    @nathanholmes4942 Рік тому +3713

    I love Rainbolt but honestly watching him just get decimated and seeing him spiral is actually really funny 🤣🤣🤣

    • @njbrx
      @njbrx Рік тому +197

      now he knows the feeling of being a mortal like us lmao

    • @soyanshumohapatra
      @soyanshumohapatra Рік тому +4

      ​@@njbrx woooooooooooooah

    • @richhobo1216
      @richhobo1216 Рік тому +27

      for real lmao, especially during the cambodia game

    • @KianTheeGreat
      @KianTheeGreat Рік тому +5

      @@soyanshumohapatra no u

    • @soyanshumohapatra
      @soyanshumohapatra Рік тому +2

      @@KianTheeGreat what?

  • @DrErikEvrard
    @DrErikEvrard Рік тому +926

    17:08 - only in Belgium parking signs MUST be on an orange pole (that was only changed in traffic law in April 2023, so most will still be orange). Also the street surface, the sidewalks and the architecture are unmistakably Belgian (definitely NOT Danish).

    • @georainbolt
      @georainbolt  Рік тому +787

      2 am moment

    • @floob247
      @floob247 Рік тому +158

      ​@@georainbolt as you always say, "cope" 😂

    • @maximumcool25
      @maximumcool25 Рік тому +2

      🤓

    • @Bigz2006
      @Bigz2006 Рік тому +10

      also the sign that says "20m" is only in belgium

    • @nancypotts9877
      @nancypotts9877 Рік тому

      The stupid kids don’t realize that they’re building technology for the current billionaires of the world who are use this technology to suppress the rest of society for the rest of human existence I mean, how dumb are these kids? They’ve created some thing that allows the police to track somebody from a simple photo I mean do they really think they’re helping society because the only ones they’re helping are the 0.01% that’s the only ones that they are helping I mean read the Bible this is demonic technology here this is the type of stuff the devil wants for complete global control .

  • @GingyNinjyy
    @GingyNinjyy Рік тому +286

    4:34 im convinced dude with the glasses is also an AI just how he sits there like that

    • @maikel07777
      @maikel07777 7 днів тому

      Bro's glasses are wiggling too

  • @ben1637
    @ben1637 Рік тому +9

    17:01 Quick tip: In Belgium, all poles that hold trafic signs concerning parking a vehicle, have to be in the orange color. This rule will change soon but they won't remove the old orange poles once it isn't a rule anymore. As far as I know, Belgium is the only country with this unique rule.

  • @thisfeatureisstupidxo
    @thisfeatureisstupidxo Рік тому +1750

    These guys are going to go far . Tech companies will be all over comp sci graduates with AI knowledge . Straight to the top

    • @jjpswfc
      @jjpswfc Рік тому +152

      True, but I think tech companies are all over a lot of post-grad/PhD Stanford students lmao

    • @richhobo1216
      @richhobo1216 Рік тому +65

      @@jjpswfc yeah just graduating from Stanford with a bachelors would get a ton of job offers, much less being a graduate/PhD student

    • @zigotina
      @zigotina Рік тому +6

      they don't even know how is it working

    • @jjpswfc
      @jjpswfc Рік тому +4

      @@richhobo1216 mhm I said post-grad. No doubt that undergrads would get a lot of offers though. Particularly with the state the comp sci industry is in rn, most people's dog could get a job somewhere if it promises to learn about machine learning.

    • @jjpswfc
      @jjpswfc Рік тому +41

      @@zigotina I feel like you have to know how it's working to make it... The only way they might not know how it's working is that they don't know exactly what it looks for and exactly what "weighting" it puts on the nodes i.e. how important are telephone poles compared to how important grass colour is.

  • @imag1n342
    @imag1n342 Рік тому +1253

    Its crazy that the only time we can humanize rainbolt is when he is against an AI 🤣

  • @andrewsowinski4725
    @andrewsowinski4725 Рік тому +1456

    I do a bit of AI for fun, and I can almost guarantee that a huge amount of the accuracy comes from meta info. It might pick up on a tiny scratch on the camera that the human eye can't even see and instantly know that it can only be within the region where the mapping car had a scratch in that exact spot. It only needs a few almost impercievable clues like that to beat people every time. I'd be curious to see how it would perform on images taken with a mapping car that was never used in the training set

    • @Zalied
      @Zalied Рік тому +45

      It should work on custom images. So you can find out what regions it only guesses on meta va what it knows. Their has to be 1 region that is pure meta

    • @andrewsowinski4725
      @andrewsowinski4725 Рік тому +150

      @Some Guy I’m not referring to actual image metadata, I mean meta info from a geoguessr sense. Referring to small hints in images such as an antenna showing up in a certain country or a rift in the sky due to improper image stitching in another

    • @andrewsowinski4725
      @andrewsowinski4725 Рік тому +13

      @Some Guy yup it’s pretty terrifying. I’m trying to keep my skills honed enough to where I can keep up when AI pair programming is industry standard, but it’s gonna get messy. I’m 25 so it’s not like I can hope to be retired before the real changes hit lol

    • @Henrix1998
      @Henrix1998 Рік тому +4

      I mean that's what he showed in the end of the video

    • @AdrianwithaW
      @AdrianwithaW Рік тому +8

      Yeah would love to give it a photo I take from out on the street and see how accurate it is - I imagine it would be, but interesting to see what might start slipping it up

  • @communityyoumustseekyoungp5630
    @communityyoumustseekyoungp5630 Рік тому +40

    I am just an average computer scientist at almost 40 y/o, but seeing this young exceptionally bright folks really brightened my day. Back in that age (well it was a bit of a different time but still) I wouldn't even be CLOSE to be able to form such well structured thoughts and programs. Congrats and I am pretty sure all those young folks have a bright future ahead! But I am sure they already know.

    • @divinecreation6
      @divinecreation6 20 днів тому

      Actually cs graduates back then were much better in average. Because now there's a lot of people flooding in cs in hope of getting a easy well paying tech job

  • @dr.dragan
    @dr.dragan Рік тому +58

    21:24 AI knew exactly where it was but chose not to be on the bridge

  • @ahhkaraj
    @ahhkaraj Рік тому +76

    The Spain guess when it was Italy at 12:25 is a perfect represation of never doubt yourself or whatever the saying was

    • @miniepicness
      @miniepicness Рік тому +9

      "trust your gut"

    • @ahhkaraj
      @ahhkaraj Рік тому +1

      @@miniepicness thanks i already forgot what it was

    • @saaaaskia
      @saaaaskia 8 місяців тому +5

      @@ahhkaraj You should've trusted your gut

    • @Raino123
      @Raino123 2 місяці тому

      Nah but his gut was also going to Spain to more that’s why he voted if he knew it was Italy more then he would’ve guessed it

  • @rydenkaye9735
    @rydenkaye9735 Рік тому +482

    My biggest question is how well does the AI handle modifiers like blur, half screen, no panning or super low time. Also you should try and use the AI for the locating real photos series you do

    • @ingerasulffs
      @ingerasulffs Рік тому +21

      I don't expect they could adapt to that out of the box.
      Edit: spelling

    • @ingerasulffs
      @ingerasulffs Рік тому +19

      Actually, on thinking about it, I think only blur would be an issue that would throw off the AI al the time. The others like half screen, no panning, and other things like upside down and mirrored and even black and white or scrambled could probably work out of the box, since the AI picks up on small things and I don't think it's bothered by where in the picture that detail is too much, or what colour.

    • @waltkowalsky4344
      @waltkowalsky4344 Рік тому +9

      Blur/half screen might work because the model wasn't trained on that. Panning wouldn't change much, it would just take 1 screenshot instead of 4. 'Super low time' doesn't really change anything because the AI takes a screenshot which is fed to the model.
      But even with blur/half screen it's just a matter of training the model on such images, which the creators can do very easily because they already have the image dataset that they can apply blur to or anything they want.

    • @rydenkaye9735
      @rydenkaye9735 Рік тому +8

      @@waltkowalsky4344 I think you're underestimating the impact that 4 pics vs 1 has. you saw in the video how much worse it did with 3 pics instead of 4 in the glitched round rainbolt almost won

    • @drapex0072
      @drapex0072 Рік тому +6

      @@rydenkaye9735 Well it wasn't just 3 pictures, it was 3 pictures plus an incorrect one. There is a saying that the only thing worse than no information is misinformation.

  • @xCokeMaanx
    @xCokeMaanx Рік тому +538

    It’s still impressive how good rainbold is. He can hold a dual with a fucking AI super pc, even if he loses.

    • @Ruzzky_Bly4t
      @Ruzzky_Bly4t Рік тому +62

      It's also kind of sad that one of the best humans stands no chance against the AI. A year ago he would win easily, now he's barely winning in Laos. This is just the beginning.

    • @Zharina
      @Zharina Рік тому

      @@Ruzzky_Bly4t Why would it be sad? It's just the natural advancement of technology. They are programmed to be better at handling specific tasks than human beings and yet without human beings, AIs are dumb as fuck.

    • @Sumirevins
      @Sumirevins Рік тому +21

      We can compare this like Gary Kasparov and Blueray Supercomputer chess match

    • @AnindyaMahajan
      @AnindyaMahajan Рік тому +24

      @@Ruzzky_Bly4t How is it sad? If anything, it's mighty impressive that a single human can be talented enough to almost stand shoulder to shoulder against an AI which is built using the collective knowledge provided by lifetime's worth of research by thousands of scientists who are most likely geniuses themselves!

    • @gichingamwaka6172
      @gichingamwaka6172 Рік тому +1

      Rainbold😮‍💨

  • @alanmccormick6911
    @alanmccormick6911 Рік тому +8

    I have a master's degree in CS / Machine learning... What they have done is incredibly impressive. I believe detecting the camera smudges though is an unfair example of over-fitting on the training data. The purpose of an AI model like this would be to take any photo of the countryside and geolocate it. Relying on the specific google street view car camera lens dirt, won't help it solve the general problem. I'm sure it can still do really well with other photos. But their explanation that it had a really small chance to have ever seen any of those specific photos is somewhat broken when a much larger percentage of those photos will have similar smudges.

    • @jonbbbb
      @jonbbbb Рік тому +4

      Agree, it would be really interesting (in the sense of being useful for humans to learn from) if they trained on random geotagged photos, not specifically google street view photos, so that it can't learn any kind of meta.

    • @alanmccormick6911
      @alanmccormick6911 Рік тому +1

      @@jonbbbb Thanks, glad someone read my comment.

    • @tomizatko3138
      @tomizatko3138 11 місяців тому

      @@jonbbbb I agree.

  • @madalyn2268
    @madalyn2268 Рік тому +6

    im so impressed with the mechanics of the AI...my roommate at college is a comp sci major and as a psych major even the lower level stuff looks crazy to learn!!! that being said this was a really awesome vid :) rainbolt's humor and the editing makes me laugh out loud

  • @nainmain
    @nainmain Рік тому +481

    This AI could be actually useful in some life or death situations where you need to locate someone as an example from an image but at the same time the AI could be used for bad things, like, stalking.

    • @Skyl3t0n
      @Skyl3t0n Рік тому +50

      Not really. It average 44km which is way too much to pinpoint someone. Maybe if it gets to under 3km

    • @nainmain
      @nainmain Рік тому +132

      @@Skyl3t0n that's better than not knowing the general area to search in

    • @zura17
      @zura17 Рік тому +160

      @@Skyl3t0n getting within 44km of osama bin laden would have been very helpful

    • @thepastarat
      @thepastarat Рік тому +29

      @@Skyl3t0n And it's also only using 4 images each guess with a very strict time limit to process them

    • @wonderseven9248
      @wonderseven9248 Рік тому +12

      Like seriously the application of this outside of just geoguessr is just massive

  • @thatverseguy
    @thatverseguy Рік тому +146

    Imagine a generation where people are using the same methods AI use to locate images. There's a lot from both worlds that look interesting in the future.

  • @Sebastian
    @Sebastian Рік тому +729

    Are you sure the students aren't robots themselves?! I mean they were completely deadpan, confident in the powers of the monster they'd built!

    • @OfficialCANVAS
      @OfficialCANVAS Рік тому +79

      Bro don't do people on the spectrum that dirty😢

    • @MrAgentTurner
      @MrAgentTurner Рік тому +5

      ​@@OfficialCANVASlol

    • @liamdonegan9042
      @liamdonegan9042 Рік тому +74

      @@OfficialCANVAS why are you assuming smart people are automatically autistic? that's a harmful stereotype

    • @alexandersmith6140
      @alexandersmith6140 Рік тому +34

      When it cut to the first shot of the two students leaning against the wooden wall, I legitimately said to myself, that one on the right is some bad CGI

    • @steviie_b
      @steviie_b Рік тому +2

      literslly man... the one kid with the screen to himself looks completely like an animation

  • @Lucien-si5yx
    @Lucien-si5yx Рік тому +178

    The sheer innate confidence of “we don’t really see any improvements we need to make right now”

    • @JordanMSeverns
      @JordanMSeverns 4 місяці тому +23

      no he said that they dont see any immediate improvements available. theyve reached near the peak of what their methodology is capable of

    • @luchodore
      @luchodore 3 місяці тому +1

      It doesn't mean the ai can't be better, they know it can be better they just don't see any obvious ways how to make it better yet.

    • @Vario69
      @Vario69 3 місяці тому +1

      "I am the ultimate lifeform"

  • @trapin4k965
    @trapin4k965 11 місяців тому +12

    I find it hilarious and extremely talented how most the time your first waypoint and guess is dead on but you move it second guessing

  • @QQ-rx9xp
    @QQ-rx9xp Рік тому +54

    Using the smudges on the camera is insanely clever, the same car will have the same smudges for quite a long time, perhaps even over multiple routes so by knowing them you can pinpoint the region. Absolutely insane, and a good example of how these models doesn’t “think” like we do.

    • @frankman2
      @frankman2 7 місяців тому +1

      I'd call it a side effect. The AI doesn't "know" what it's doing

    • @addenanda
      @addenanda 6 місяців тому

      ​@@frankman2they know what they doing. they have objective. and only care about that

    • @sergeybessmertny2819
      @sergeybessmertny2819 2 місяці тому +1

      It’s called meta and humans heavily rely on meta too, just different one. It’s really rarely about soil, vegetation and road signs or architecture. I watched competitions, they all notice first camera angles, camera types, reflections and distortions, post processing, weather, lighting and season, contrast and color temperature and all of that and judge location based on that. Dirt on camera used in some location, just humans are jot very great at noticing small ones, we are all trained to ignore them when we look through windows and screens

  • @nolancarr6725
    @nolancarr6725 Рік тому +50

    Does anyone else think the dudes look like they have ai faces?

  • @dfg12382
    @dfg12382 Рік тому +99

    Now take the 3 AIs you've played and let them team up in a pro tournament.

    • @brosaus
      @brosaus Рік тому +9

      Nah just 1. The AI is cracked and need the nerf

  • @justgame5508
    @justgame5508 Рік тому +2404

    Why do the researchers look like they were generated by AI

    • @regd6060
      @regd6060 7 місяців тому +19

      they don't

    • @moromlike8008
      @moromlike8008 7 місяців тому

      ​​@@regd6060they do honestly

    • @DN-jm2xg
      @DN-jm2xg 7 місяців тому +220

      @@regd6060 they do

    • @cloutchx
      @cloutchx 7 місяців тому +20

      Thats crazy fr

    • @dougiewarz6232
      @dougiewarz6232 7 місяців тому +23

      @@regd6060 they do

  • @pinkdragon4830
    @pinkdragon4830 Рік тому +42

    Idk why but seeing Rainbolt make a better guess than the AI is so exciting

    • @jackd9375
      @jackd9375 6 місяців тому

      You don’t know why

  • @shreyas3479
    @shreyas3479 Рік тому +55

    Thats no AI. Its your lost twin that they have kidnapped and trapped in the basement.

  • @aurifomo6385
    @aurifomo6385 Рік тому +238

    Sorry I can't tell why but those two AI guys look like some supervillains

    • @HeadOnAStick
      @HeadOnAStick Рік тому +42

      ikr, I was waiting for the dude with the glasses and piled up hair to steeple his fingers and say "soon the world will be mine, bwahahahaha!"

    • @buildintotrains
      @buildintotrains Рік тому +15

      why is their skin so perfect too

    • @nicholash1278
      @nicholash1278 Рік тому

      i hate them so much

    • @yo25999
      @yo25999 Рік тому

      ai filter@@buildintotrains

    • @Ligmaballin
      @Ligmaballin 8 місяців тому

      Glasses and the sweatshirt

  • @falan9021
    @falan9021 Рік тому +15

    Those last rounds are basically Terminator 3, the Termanitor teaming up with the humans against a newer, better version of itself. :D

  • @missinglegs
    @missinglegs Рік тому +32

    From my understanding of Ai fun fact: even if it has seen these locations before, it wouldn't be able to just 5000 them, because it doesn't retain data on individual locations, it only learns from them to improve its overall ability, it adjusts the patterns it looks for based on the information the locations provide

    • @klauspeter2199
      @klauspeter2199 Рік тому +4

      I don't know much about neural networks either, but from what I've understood overfitting and therefore making a model remember a dataset too well is definitely a thing.

    • @TheJulianmc
      @TheJulianmc 4 місяці тому

      Wrooooooooong

    • @missinglegs
      @missinglegs 4 місяці тому

      @@TheJulianmc it is? Could you elaborate?

    • @9308323
      @9308323 Місяць тому

      ​@@klauspeter2199 Yes, but also could be highly inefficient, depending on what you want it to do and how much you want to brute-force it. Not to mention that it could make more mistakes if something doesn't totally fit its data. It's why most neural network AIs don't do that and they try to generalize from the beginning. Otherwise, you get an AI that learns to go to the green pixel instead of the exit sign.

  • @trizzybones
    @trizzybones Рік тому +27

    If the AI is using camera smudges as a meta, that's a bummer cuz then it's really picking up on image artifacts from those specific google streetview photosets instead of understanding the actual location and scenery on a deeper level, so the application of the AI is only limited to the game and not wider uses like digital forensics and such. That said, I'm sure it has other metas that don't include just photoset specific artifacts, but I wonder to what extent.

    • @justlola417
      @justlola417 7 місяців тому +2

      That's what I was thinking too, it can win at geoguesser but it may depend on these meta informations instead of the actual location

    • @Manwith6secondmemory
      @Manwith6secondmemory 4 місяці тому

      Its objective is to get the highest score I think so its going to go meta just like a human would.

    • @dscarmo
      @dscarmo Місяць тому

      This happens in most AI problems involving images, its understanding differences in imaging data noise signatures that a human would not be able to detect

  • @alwaystired1
    @alwaystired1 Рік тому +113

    i feel like the AI would do a frighteningly good job with the dirt maps

  • @Sebastian
    @Sebastian Рік тому +41

    2K likes attained, so expecting the rematch of the human pros vs. the AI!!! Your reaction on every round was priceless, clinging to the hope you'd win at least one game!

  • @tbkih
    @tbkih Рік тому +306

    The students faces are also AI generated, nice

    • @Tyler_18_
      @Tyler_18_ 9 місяців тому +5

      Lmao my thought exactly

    • @enrott8560
      @enrott8560 9 місяців тому +24

      nah thats just how germans look

    • @kylehankins5988
      @kylehankins5988 3 місяці тому

      I thought the same thing lol

  • @Cau_stix
    @Cau_stix Рік тому +9

    I am fascinated and somewhat afraid of AI’s capabilities. Who knows, how advanced it could get. Something tells me AI will be coding AI soon. But overall a very well made and interesting video rainbolt. Loving the content and to see you and your friends so humble and happy.

  • @longlong1773
    @longlong1773 5 місяців тому +7

    bro got cooked the frustration on his face when he loses the cambodia match to pigeon🤣

  • @RRproductionsTV
    @RRproductionsTV Рік тому +327

    the fact the AI learns so quickly from going basically not knowing which continent to being able to 5k quite easily is astounding, but also scary as fuck. At some point you can no longer even keep up.

    • @seventeen777
      @seventeen777 Рік тому +58

      Its pretty much what happened to chess, we're now at the tipping point where AIs are starting to beat the best geo players, and eventually they'll be good enough to discover new metas that allow people to guess more accurately than they ever could now.

    • @asgasgasfasfad
      @asgasgasfasfad Рік тому +28

      @@seventeen777 What lol chess engines first beat the world champion in 1997... A chess engine ran on my toaster would 10-0 Magnus Carlson with ease. Engines are no longer a competition they're the answer to what you should've done.

    • @seventeen777
      @seventeen777 Рік тому +36

      @Asdasdasa exactly what I said. I was using chess as an example of how geo ai will likely play out in the next couple decades, since so far it has followed the exact same path as chess

    • @asgasgasfasfad
      @asgasgasfasfad Рік тому +11

      @@seventeen777 Sorry thought you meant that the tipping point was in chess and not geo

    • @Grunk369
      @Grunk369 Рік тому

      Yeah, this will happen with literally everything. Human supremacy is coming to an end, we’re being replaced in every aspect aside from manual labor

  • @dvorszkydavid9140
    @dvorszkydavid9140 Рік тому +31

    Laos has very small coverage, and you need a relatively large dataset to train an AI that can classify images with this precision. Based on this, I assume the AI has seen almost all Laos locations and failed on the ones that weren't in the training set. Still very impressive, tho

  • @Iambestforreal
    @Iambestforreal Рік тому +31

    Watching trevor slowly being more upset/sweaty is so funny i dont even know how lol

  • @swannnny
    @swannnny 3 дні тому +1

    I don't think people quite understand how crazy it is that this guy is taking rounds off of an AI, that is mindblowing, this guys brain needs to be looked at

  • @ArtoriaTheKing
    @ArtoriaTheKing 9 місяців тому +12

    Nah, but making an AI that can make an educated guess from the smudges on the camera is genuinely insane, props to those guys for making such a beast

    • @ienjoysandwiches
      @ienjoysandwiches 2 місяці тому +2

      But then it's not geoguessing anymore, it's camera smudge guessing

  • @theauldscientist
    @theauldscientist Рік тому +27

    16:20 is literally the house I grew up in. How spooky is that!

  • @23desdfe345r2fd23f23
    @23desdfe345r2fd23f23 Рік тому +13

    they need to make this AI output the strongest feature combinations which led to its decision.
    Thus, the AI can train you to discover more metas, and then you will stand a better chance against it.

  • @princeveegeta8700
    @princeveegeta8700 Рік тому +6

    "Do I feel good about that? No that feels like such an underhand pitch."
    *Kiwis looking over at the Ozzies* 😂

  • @leogr1003
    @leogr1003 Рік тому +5

    Color balance is probably something AI cues off of that is just impossible for humans to match. Some cameras might have a slight blue hue to them, or might have different levels of saturation, etc etc

  • @brianarsuaga5008
    @brianarsuaga5008 Рік тому +4

    These guys probably have a ready-to-go company when they're done with school

  • @WillyWoxy
    @WillyWoxy Рік тому +4

    This is wild... really great work from these guys honestly that must feel hella rewarding

  • @alansmithee419
    @alansmithee419 Рік тому +79

    I liked the bit where the AI went "It's intelligencing time" and intelligenced all over Rainbolt.

  • @x9x9x9x9x9
    @x9x9x9x9x9 Рік тому +70

    That AI has a future as a tool for detective work. That's crazy.

    • @Ruzzky_Bly4t
      @Ruzzky_Bly4t Рік тому +10

      It also has a future for stalking purposes.

    • @casualfool122
      @casualfool122 Рік тому

      ​@@Ruzzky_Bly4t probably not for public use if I was to guess bro

    • @johnwig285
      @johnwig285 Рік тому +1

      ​@@Ruzzky_Bly4t i mean u can get the person's location from exif data, u don't even need AI i.e. recognition to get someone's location off his pics

    • @Pharoah2
      @Pharoah2 Рік тому

      @@casualfool122once they publish the paper it wouldnt take much to read it and re-implement it yourself if you have decent CS knowledge and had a good GPU. Once one person does that itll be readily available.

    • @casualfool122
      @casualfool122 Рік тому

      @@Pharoah2 maybe, but the chances of it spreading enough to where its readily available for stalkers wouldn't be extremely rapid by any means. and that's only if it actually gets spread at all

  • @jamypad5251
    @jamypad5251 2 дні тому +1

    Rainbolt is extremely cute when he's so focused ☺️☺️

  • @kylecampbell3
    @kylecampbell3 Рік тому +1

    this can easily translate into crime investigation. missing persons, etc. trying to find someones location with only an image, or video. amazing work.

  • @Benw8888
    @Benw8888 Рік тому +8

    You can always improve performance by just scaling up the model, but using CLIP is probably the best architecture they could use at the moment so no obvious ways to create big jumps. (Besides giving it more images than 4 to guess from and just training it a lot more)

  • @barmetler
    @barmetler Рік тому +12

    I do have to say, if you want to get into neural networks, this would be the perfect project to start out on. It is incredibly simple to get to work (maybe not to work well, but to work at all)
    Basically, you have an input image, like in many neural networks you can see online, and you output an x and y coordinate. And even better: you could not ask for a better dataset for training than what google or microsoft have to offer, I mean there are billions of images, it's amazing. So perfect starter project!

  • @perplexedon9834
    @perplexedon9834 Рік тому +8

    I've got a feeling that it's subtly picking up on camera discrepancies to be very accurate country-wise. Maybe it can identify the noise pattern of the specific camera sensors, and has a large enough sample of locations that it's seen something from almost every Google street car.

  • @TheXientist
    @TheXientist Рік тому +7

    I gotta say i am slightly disappointed by the fact that the AI used the streetview camera imperfections to guess. It kind of defeats the whole purpose of geoguessr and geolocation from a single impression, and means that the AI would perform much worse when used with photos taken with random cameras when trying to for example locate missing people.

  • @vestlen
    @vestlen Рік тому +10

    Assuming this will also work on custom images and not just street view images, I wonder if these students realized that they have just invented a way for anyone to locate the origin of pretty much any outdoor picture or video since the beginning of time. It will take a lot of tweaking, and the farther back you go to the harder the model training will get, but that would be the next logical step for this technology. It’s honestly hard to fathom.

  • @_Matchu
    @_Matchu Рік тому +5

    "my geoguessr career is obviously over now so if you guys have any ideas for what i could do..." LMAO

  • @plebiain
    @plebiain Рік тому +8

    I really want to see a game with like 10 pros against this AI. Would be the ultimate showdown

  • @dude135791000
    @dude135791000 Рік тому +7

    We're going to need to assemble the Geoguessr Avengers to take on this Ultron.

  • @2dreamy
    @2dreamy Рік тому +2

    15:29 "If you can't beat em', Join em' Germany." - Rainbolt 2023

  • @smala017
    @smala017 Рік тому +4

    Training the AI on 1 in 1000 street view images definitely does not count as "virtually impossible" that it's ever seen any of these rounds before.

  • @StygianNightmare
    @StygianNightmare Рік тому +20

    Dude it's an AI AND it's 4 very smart minds putting that ai together against 1. You did amazing bro

    • @Alkis05
      @Alkis05 Рік тому +1

      Saying that today for this kind of test shows how long this technology came. No one would believe it possible a couple decades ago.

  • @geoshifu4356
    @geoshifu4356 Рік тому +143

    wanna see stique playing against it

  • @SadMatte
    @SadMatte Рік тому +89

    The unfortunate part about this is that this probably could be the end of AIs in tourneys, which was really fun, but now they're too good...

    • @Gameboygenius
      @Gameboygenius Рік тому

      Could still be doable with a team of humans so you get a little hedging going.

    • @kingt0295
      @kingt0295 Рік тому +17

      @@Gameboygenius just give up theyve replaced us 🤖🦾

    • @Ruzzky_Bly4t
      @Ruzzky_Bly4t Рік тому

      @@Gameboygenius Give the AI another 2 years, and it will probably destroy 10 pro players at once.

    • @eVill420
      @eVill420 Рік тому

      @Some Guy actually, the military's technology isn't any better. mostly because developing AI like this costs a lot, takes a lot of time and has limited military uses.
      China has the facial recognition stuff, that's probably the closest equivalent
      after all, scientists figured out HOW to make an atom bomb years before they found the real method

    • @stov3764
      @stov3764 Рік тому

      well it has been the case for a few years now already (cf Deep Blue for example)

  • @lastnamefirstname8655
    @lastnamefirstname8655 Рік тому +1

    this truly was so amazing to see. ai has improved and is capable of doing so much. this is very impressive. well done as well, though, rainbolt! humans vs ai in geoguessr must continue, defend humanity's honor!

  • @JLCxGRU
    @JLCxGRU 4 місяці тому +1

    great video! this is epic! Love the content

  • @Daniele.Rossini
    @Daniele.Rossini Рік тому +4

    Wow! It's like watching Magnus Carlsen play stockfish! He could give a nice fight but all can he hopes is to make a draw!
    And following this analogy, the last game is like you started the game with a piece odd!
    So fassinating and beautiful! Can't wait for the next video!

  • @aimeeaidanu
    @aimeeaidanu Рік тому +5

    I don't know why but I laughed so hard when he said that they were "quivering in their boots" lmao

  • @edvardpiano
    @edvardpiano Рік тому +5

    probs people said already but looking at what the ai sees for tough countries could unlock tons of new metas!

  • @physics_enthusiast_Soorya
    @physics_enthusiast_Soorya 3 місяці тому +1

    Hey! That was alot of fun! I really enjoyed this video :)
    It's okay if you feel defeated. Don't worry, You can do really better in the future. Just don't give up ✨️
    Thanks alot for Uploading this video ^-^

  • @gamingghostxd3965
    @gamingghostxd3965 Рік тому +2

    'Could be finland but I like sweden' that's how to guess the location right there

  • @MatthewBaka
    @MatthewBaka Рік тому +6

    5 GeoGusesr Pros vs 1 AI is such a great idea

  • @Its_McItaly
    @Its_McItaly Рік тому +10

    Love the trash talking of the AI LOL

  • @shaneyboy619
    @shaneyboy619 Рік тому +7

    Yo that was crazy when he picked Spain over Italy and lost, I've lived in Spain most of my life and felt 100% confident that was Spain 😮

  • @vengerseven
    @vengerseven 8 місяців тому +1

    Rainbolt is the kind of man, that if you were to kidnap him, he would immediately say "uhm, I'm going to guess Costești Romania locking it in."

  • @MTLud
    @MTLud Рік тому +1

    Bro your an actual machine, love the content!!

  • @DeepRenders
    @DeepRenders Рік тому +8

    11:35 bro the AI will get revenge for that later

  • @PaTaku7
    @PaTaku7 Рік тому +12

    The whole video I sat there nail biting and hoping Rain would at least get one W!

  • @sevrock1014
    @sevrock1014 Рік тому +5

    Pretty sure this is the part where Rainbolt goes into hiding forever…

  • @punizika
    @punizika 11 місяців тому

    for Brazil, I don't know if is feasible or not to learn but the area code from phone numbers are a two digit number prefix right at the start. So here at 3:46 bellow "Racco" there's the 61 area code from the phone number, which means this is from Goiás/Federal District area.

  • @leviielge
    @leviielge Рік тому +1

    "guys I sat there and walked every single street" 🤣🤣 I'm rolling

  • @toasteroven6761
    @toasteroven6761 Рік тому +14

    I propose they name the Pigeon AI "Lockbird" both in honor of Stockfish 15 (best Chess AI) *and because the bird was more locked-in than any human I've seen.*
    This new AI has the potential to be just like Stockfish which helps Chess players learn new things about chess via post-game analysis of their online or OTB games. Great video, and great work Stanford students!
    [Geogusser AI fan-boy warning]:
    Lockbird will probably many times better than any human by Lockbird 15 [if development continues for as long as Stockfish has been developed that is] just like Stockfish 15 already is.

  • @photojeremy
    @photojeremy Рік тому +7

    would be interesting to see a rematch not using geogessr, but just photos of different places. then the AI training data might become much less useful (like the smudges), so it would be interesting to see how well that knowledge transfers.

    • @Kochen51
      @Kochen51 Рік тому +1

      Maybe I heard wrong, but didn't they say at some point that they didn't based it on Geoguessr but on random Google Streetview? That would mean that it would do even better

    • @ORCIproductions
      @ORCIproductions Рік тому +3

      @@Kochen51 geoguessr is streetview

    • @Kochen51
      @Kochen51 Рік тому

      @@ORCIproductions yes but it's a database of some of the locations, not every point in the world, right? The spawn points

  • @RAMMY237
    @RAMMY237 Рік тому +4

    AI is AI, but the fact that this guy picks the location, then changes it a little bit couple of times, and it turns out his very first pick was the closest ever. Absolutely inhuman skill. And how funny when exact same place pops up, but he clicks farther than in those previous cases :D
    Btw, is AI able to pick exact same place if the same image re-appears in the next round?

  • @300andDeadStraight
    @300andDeadStraight Рік тому +2

    Rainbolt losing his mind on video for us to enjoy. This is quality content and I loved every minute.

  • @pressstart198
    @pressstart198 Рік тому +2

    Bro lost to AI by not guessing Cape Cod two times in a row.

  • @michaelbeckett6319
    @michaelbeckett6319 Рік тому +4

    Good for Kelvin from Sons of the Forest to be a part of this brilliant team. Some intelligence between them.

  • @duskden2
    @duskden2 Рік тому +12

    They got us bro.

    • @georainbolt
      @georainbolt  Рік тому +15

      i bet it’s trash at india dusky

    • @duskden2
      @duskden2 Рік тому +9

      @@georainbolt fr bro ain't ready for that smoke on India.

  • @notsogood2576
    @notsogood2576 Рік тому +19

    11:20 dude really trashtalked AI 💀

  • @asterix7912
    @asterix7912 4 місяці тому

    Thanks I really needed the label for which one was which in the thumbnail considering rainbolt does have the stature of Arnold Schwarzenegger. Love the video ❤

  • @Bit5tream
    @Bit5tream 3 місяці тому

    Sawasdii khrap 🙏 Very interesting video rainbolt. AI has improved vastly since this video, would love a more recent challenge video.