How AI Powers Self-Driving Tesla with Elon Musk and Andrej Karpathy

Поделиться
HTML-код
  • Опубликовано: 24 ноя 2024

Комментарии • 137

  • @austinryder9028
    @austinryder9028 3 года назад +163

    I had to double-check that I wasn’t on 2X playback speed

    • @renaissanceman622
      @renaissanceman622 3 года назад +4

      Yep. I did too!

    • @AdrianMeredith
      @AdrianMeredith 3 года назад +15

      the video has been sped up, he isn't just talking fast but moving fast too. 0.75 is better

    • @brandonbarr2784
      @brandonbarr2784 2 года назад

      He has the chip in his brain

    • @jonathanqamanzi
      @jonathanqamanzi 2 года назад

      I swear to God me too

    • @karenzhao4629
      @karenzhao4629 2 года назад

      I didn’t see your comment before, I did exactly the same thing

  • @vermack
    @vermack 3 года назад +11

    The ability to source any type of examples from the fleet is amazing!

  • @dhruvpatel4948
    @dhruvpatel4948 3 года назад +20

    That moment when Elon reminds Andrej about CS231 😅😅

  • @kaleygoode1681
    @kaleygoode1681 3 года назад +76

    Andrej sounds totally normal if you set playback speed to 0.75x...
    His brain is running a third faster than most people!
    NeuraLink is going to be interesting when communication is no longer the current slow speed speach...

    • @editg121
      @editg121 3 года назад +2

      A third is understatement

    • @markhealth3386
      @markhealth3386 3 года назад +6

      OMG ... So true. thanks for the tip 😃

    • @zantetsu8674
      @zantetsu8674 Год назад +5

      The video has been sped up, apparently by around 1.25x. Unfortunately needs 0.8x on the playback to make it correct but that's not available. 0.75x makes the playback a little bit too slow. So you either get too slow (0.75x playback) or too fast (1.0x playback). Not sure why the person who posted this video sped it up like that.

    • @MartinCapodici
      @MartinCapodici Год назад +1

      I had to check my settings, he made me think I changed it to 1.5 !

    • @deveshbhatt4063
      @deveshbhatt4063 11 месяцев назад

      @@zantetsu8674 seems like you haven't heard Andrej speak.

  • @aaronbounds1336
    @aaronbounds1336 3 года назад +3

    There are some pretty big high-level takeaways here: using pure vision with a slight hint of radar, for now, to get lidar like accuracy in terms of depth perception. This is major.

  • @andyandreou
    @andyandreou 3 года назад +6

    That image of the fleet data on a map at 12:24 is absolutely stunning. I'm from Cyprus, and even though we don't have Tesla showrooms, superchargers or service centres I can see that Tesla is still collecting data from the cars which were imported here.

  • @PierreH1968
    @PierreH1968 3 года назад +7

    This is awesome!... I wish the Teslas have the aerial camera view by combining all 8 cams to show all around the car. Like BMW does on their cars

    • @fredepstein
      @fredepstein 3 года назад +1

      There is no front bumper camera for doing that.

    • @PierreH1968
      @PierreH1968 3 года назад

      @@fredepstein that makes sense!... but i think you can project images from the front cameras with a transform to fit the road in front.

    • @fredepstein
      @fredepstein 3 года назад

      @@PierreH1968 not possible because the camera can not see just in front the bumper.

  • @peterprocopio2192
    @peterprocopio2192 3 года назад +10

    What a great video on AI and neural networks. Amazing future. Tesla is well positioned to remain in the lead with autonomous vehicles because they have so many cars in the field gathering data and teaching its neural network. No one else is in the game.

  • @psbjr
    @psbjr 3 года назад +19

    very powerful hot dog/not hot dog technologies, thanks for sharing

    • @rabbitlissa
      @rabbitlissa Год назад +1

      Jian Yang must be super proud

  • @silberlinie
    @silberlinie 3 года назад +4

    14:56 to 15:55,
    how long does the iterative run of the data
    engine take to complete the cycle? Seconds?
    Minutes? Days?
    And how often is an update sent to the fleet?
    Every day? Every week?
    17:32,
    all examples coming from the fleet will be
    annotated, so are all the half million examples
    annotated by hand by people?
    And,
    how long does it take to download an new
    update to the car?

    • @jacksontriffon5064
      @jacksontriffon5064 3 года назад

      Keen to know

    • @UniqueApparently
      @UniqueApparently 3 года назад +1

      Fleet examples are automatically annotated mainly by Dojo (their massive cluster) and anything with a low confidence score get human input, making the ai smarter. Asking the fleet and getting correct answers is a measure of the algorithms accuracy.
      Updates come to the fleet about once per month in the main updates, hard to say which of the smaller ones are streamed and when.

    • @silberlinie
      @silberlinie 3 года назад

      @@UniqueApparently You will surely get a message if an
      update has happened.
      And surely also a message about when that was.
      Don't you have a history to retrieve?
      And also what name they all have.
      And what size.
      This must be somewhere in the screen menu
      to be called up?

    • @UniqueApparently
      @UniqueApparently 3 года назад

      @@silberlinie The updates only come in mass stages as official releases, not individually as tiny packages. You can auto-apply them when notified of readiness, or just delay or ignore them.
      Sometimes they have names like "V10" or "Holiday update" but usually are labeled with their release number or git hash, and can be tracked here teslascope.com/teslapedia/software

    • @silberlinie
      @silberlinie 3 года назад

      @@UniqueApparently The updates come via WLAN?
      And also via cell phone network?
      Or can you define that yourself?
      Do you have to be in park mode for that?
      Or is it also possible while driving?
      Can you watch yourself when it srartet
      and finished, so you can see how long
      it takes?
      On the Teslascope page there is no
      information about the MBytes of each packet,
      what do you know about that?

  • @XX-pq9mb
    @XX-pq9mb 2 года назад +1

    The future of communication speed of mankind is evolving into something that eventutally will sound like R2D2... Andrej is only the first phase of this

  • @tylerbradshaw7957
    @tylerbradshaw7957 3 года назад +13

    Is this on fast forward for anyone else?

    • @DesmondCheung
      @DesmondCheung 3 года назад +1

      at 0.75 playback speed, it sounds about right.

    • @readyplayersid
      @readyplayersid 3 года назад +2

      No they just live life on 1.25x

  • @nalinbranden
    @nalinbranden 3 года назад

    Awesome presentation.
    Question: when he says '"fleet" that means all the autopilot enables Tesla cars currently owned by public, or a dedicated fleet (purely for testing) of Teslas driven all around the world by a group of Tesla employees or contractors?

  • @qwerty-tf4zn
    @qwerty-tf4zn 3 года назад

    Thanks for the delivery

  • @TheKoekiemonster1234
    @TheKoekiemonster1234 3 года назад +2

    I like how elon chipped in when the guy got nervous. Great team!

  • @smhninja3746
    @smhninja3746 3 года назад +2

    Did I go slow or is this video sled up?

  • @justchary
    @justchary Год назад

    What an amazing presentation! Thank you

  • @torstenziegler4826
    @torstenziegler4826 3 года назад +2

    Thank you!

  • @michelspeiser5789
    @michelspeiser5789 2 года назад +1

    Just wanted to turn down from 1.5x speed, but saw the video was playing at normal 1x speed...

  • @X_platform
    @X_platform 3 года назад +2

    What did you use to query the fleet? How can you guarantee the search engine return all the correct result?

    • @malikhamza9286
      @malikhamza9286 3 года назад

      They already said machine Learning Mechanism to do this.

    • @X_platform
      @X_platform 3 года назад

      @@malikhamza9286 Sounds like a chicken and egg problem. If ML is perfect, it will return all the correct results; but if ML is perfect, they would not need to query and label these images.

    • @dogmatichobbyist4575
      @dogmatichobbyist4575 3 года назад

      @@X_platform doesnt have to be perfect when such influx of data is coming in

    • @pc_screen5478
      @pc_screen5478 3 года назад +1

      They could be using a larger, more accurate but slower network to do this automatically. Consider that FSD has to run in real time on relatively modest hardware compared to what tesla has at their disposal for actually training the network. They could also be simply looking for moments where the network is uncertain about what it's looking at, and that should generally be good enough to get desirable results

  • @X_platform
    @X_platform 3 года назад +4

    Why use neural net to predict depth if you always already have the ground truth from Tesla’s sensor?

    • @X_platform
      @X_platform 3 года назад +2

      Oh the sensor only give sparse data points, neural net will predict every pixel and their distance

    • @patrickjdarrow
      @patrickjdarrow 3 года назад +1

      And 1 sensor is cheaper than 2 😬

    • @fredepstein
      @fredepstein 3 года назад +1

      The sensors can not see far enough.

  • @Maverick5588
    @Maverick5588 3 года назад +5

    Why does it seem like his speaking is sped up? Is this video speed increased

    • @pearlfinder1
      @pearlfinder1 3 года назад +2

      I put speed at .75 to hear it properly

  • @PierreH1968
    @PierreH1968 3 года назад +4

    Lidar is bad with object densities, works badly in the heavy rain and cannot make the difference between an opaque plastic bag and a rock...

  • @vermack
    @vermack 3 года назад

    I don't understand one thing with Tesla cars is what happens when they are not connected to the network for long periods of time? Also, I'm sure these cars are going to be shipped with the Starlink receivers in the near future in some sort of miniature forms.

    • @lmcclymont
      @lmcclymont 2 года назад

      The car doesn’t use network for self driving, the relevant code is stored on the car’s computer (twice). The only difference is updates and route planning.

  • @Abhishekkumar-qj6hb
    @Abhishekkumar-qj6hb Год назад

    So basically you guys are utilising the fleet for getting varied data and also ensuring if the model works fine and if it fails then again quickly train the model on those groups of datasets to make the model more robust!!! Interesting
    However how far are we from the moment where we kind of act well as humans do with just very few datasets ???
    Cuz what we are doing is statistical inference on the basis of large datasets ! So it's basically good datasets and good compute as mentioned earlier

  • @posthocprior
    @posthocprior 3 года назад

    Is this true, that Tesla is primarily concerned with image detection? Driving requires so many skills: the understanding of basic physics, understanding when objects are static and don't move and when they're dynamic... How does Tesla incorporate all these other concerns into their models?

    • @edwardolvera5280
      @edwardolvera5280 2 года назад

      They cant
      Thats why the Teslas keep crashing.

    • @Ran_Dhir_Singh
      @Ran_Dhir_Singh Год назад

      I think he explained they are using drivers as training data as how the drive cars to maneuver the car based on the steering ,wheel etc. Might need more progress on that tho .19:30

  • @BryanFletcher
    @BryanFletcher 3 года назад +2

    Still... Such a powerful talk!

  • @gregorythompson8627
    @gregorythompson8627 2 года назад +1

    Wouldn't it still be a good idea to include lidar devices in some of the cars with FSD so you have can have a ridiculously large dataset for unsupervised training, image -> point cloud?

    • @turtleking9999
      @turtleking9999 2 года назад

      That's what I'm inferring they're doing, because they explicitly said it's possible to do exactly that. However they did double back and said they could train on distance without it anyway.

  • @dtibor5903
    @dtibor5903 3 года назад

    Human drivers have accelerometers and microphones built-in that should be used too for self driving cars

  • @Diarkia124
    @Diarkia124 3 года назад +1

    It's weird to think I've watched this guy before he got into neutral networks. Glad to see badmephisto is doing well

    • @anujnm6597
      @anujnm6597 2 года назад

      Same here....I learned advance cross and look ahead from his videos.

    • @clawdeckcd3018
      @clawdeckcd3018 Год назад

      I learned a lot about AI thanks to Andrej videos, he is a talented teacher, no doubt. But never heard about that Mephisto, so I checked, and yes, sure that's his voice,
      especially here: ruclips.net/video/WhPjlnWbtS8/видео.html
      I could'nt believe it.

  • @SyedAli-du9iq
    @SyedAli-du9iq 3 года назад +3

    Shut up Elon musk and let the smart guy talk

  • @MichelConrado1
    @MichelConrado1 3 года назад +4

    This is genial!

  • @sidkapoor9085
    @sidkapoor9085 3 года назад

    How are half a million images annotated? Is it done manually?

    • @nightlessbaron
      @nightlessbaron 3 года назад

      Normally yes, but there are also methods to make it semi-automated, you can check active learning.

    • @lmcclymont
      @lmcclymont 2 года назад

      This is now mostly done automatically

  • @Qattea
    @Qattea 3 года назад +1

    The fact that his last name is Karpathy

    • @Qattea
      @Qattea 3 года назад +2

      @@timurishuov5141 I mean since he’s working on AI for cars following roads (paths)

  • @jonathanqamanzi
    @jonathanqamanzi 2 года назад

    I had to double check playback speed and actually put it at 0.75x

  • @RyanSmithPhoto
    @RyanSmithPhoto 3 года назад +1

    Now if they could just make it so my car doesn't hit the brakes like mad when another car is turning across my lane of traffic. It seems like the AI should be able to tell at the speed the car is moving it would be long out of my way and doesn't slam on the brakes. I wish they had an option in the car to report when the AI does something wrong.

  • @colinmaharaj
    @colinmaharaj 3 года назад

    Can I enroll in these courses that teaches neural networks

  • @sylvaingirard
    @sylvaingirard 3 года назад +5

    Imagine being an annotater at Tesla. What a mind numbing job that must be…

  • @leedsbutler3567
    @leedsbutler3567 2 года назад

    I'm absolutely blown away. This is true AI.

  • @zardi9083
    @zardi9083 11 месяцев назад

    Set playback speed to 2x to fully understand what is happening in Andrej's brain

  • @PierreH1968
    @PierreH1968 3 года назад +7

    Tesla has it right, an AI taught to replace humans should see like humans. Not only interact with the road but also with the environment. and the evil is in the details... The long tail.

  • @DiZhaoairj23
    @DiZhaoairj23 3 года назад +14

    This is how I imagine some ai dude speaking. 2x the normal speed

    • @oxente_aquarios
      @oxente_aquarios 3 года назад +1

      Lol so true

    • @mattfairman8585
      @mattfairman8585 3 года назад +2

      I had to slow my playback speed to 0.75 to understand him lol.

    • @liarzdice
      @liarzdice 3 года назад +1

      @@mattfairman8585 LMAO I always wondered what the point of that feature was .. Now I know.

  • @parent5x
    @parent5x 2 года назад

    Another beautiful brilliant mind.

  • @lkd982
    @lkd982 2 года назад

    I heard Musk say it. 11:55 "You can't. There's no way". Where is my prizemoney??

  • @marcopaluszny
    @marcopaluszny 3 года назад

    Lidar hit job?

  • @harshaaa2k
    @harshaaa2k Месяц назад

    yes youre watching this at 1x

  • @markhealth3386
    @markhealth3386 3 года назад +1

    Kar-pathy .... Like psychopathy for cars... how ironic that's his last name

  • @jamespatrick5348
    @jamespatrick5348 2 года назад

    There may not be sufficient number of edge case images to perfect the neural net. This limitation is crucial and may not be solvable.

  • @Yurost1
    @Yurost1 3 года назад

    Hey OEMs, pay us and we will license our suite of hardware and software. We will be sure your cars are just one update behind ours always.

  • @ainnovation6967
    @ainnovation6967 3 года назад

    Fast talker is also fast Mathematics problems solver.

  • @theLowestPointInMyLife
    @theLowestPointInMyLife Год назад

    Walt and Gale vibes

  • @ntluan2k
    @ntluan2k 3 года назад +4

    Understand why Tesla is going so fast

  • @gauravrai5784
    @gauravrai5784 3 года назад

    Me with 4 GB RAM machine:
    Interesting 😯😯😮

    • @Splish_Splash
      @Splish_Splash Год назад

      it doesn't rely much on RAM, it's more about GPU

  • @suissdagout5153
    @suissdagout5153 Год назад

    Missiles making

  • @muhammedsauod9901
    @muhammedsauod9901 Год назад

    wow👏

  • @JerryMetal
    @JerryMetal 2 года назад

    Wouldn't your car need a freakin' super computer onboard to run this neural net??

    • @lmcclymont
      @lmcclymont 2 года назад

      The fact it works on their own chip is one of the most underrated thing Tesla has done tbh. The training is done back at Tesla and tHe nets are downloaded to the car so it can drive. Other cars have massive computers in the boot.

    • @TheGenerationGapPodcast
      @TheGenerationGapPodcast Год назад

      No, training of neuronet needs a gpu,s and tpu's running models already trained can on cellphone or raspberry pies

  • @yondaimehokage2281
    @yondaimehokage2281 3 года назад +1

    If I had a tesla, I wouldn't care about them taking images from my car to improve fsd. Go Tesla!

  • @techsource2235
    @techsource2235 3 года назад +1

    Another reason I believe that human body, brain, neuro system was actually PLANNED, THOUGHT THROUGH, DESIGNED by the SUPREME being, God! If it takes so much planning and efforts from people to design a limited version of AI software, its logic etc. I will never believe there is no God. There is God and He came to live among us in the person of Jesus from Nazareth.

  • @pocok5000
    @pocok5000 Год назад

    the good old days when Musk wasn't a total nutjob

  • @dogefromthefuture
    @dogefromthefuture 2 года назад

    and this whole thing ended up being a dead end?

  • @janmolski
    @janmolski 2 года назад

    Andrej always speeks 1.5x

  • @essentials9302
    @essentials9302 2 года назад

    Elon musk is like /|:

  • @semtex6412
    @semtex6412 3 года назад +1

    does he really talk like that? he sounds like a stephen hawking's computer

  • @SyncedJay
    @SyncedJay 3 года назад

    Play this video in 0.75 your welcome

  • @edwardolvera5280
    @edwardolvera5280 2 года назад +1

    Mercedes-benz is already level 3
    this weirdo has no noticed it yet

    • @lmcclymont
      @lmcclymont 2 года назад

      It is L3 on certain roads under 30mph 😂. Tesla is almost L3 anywhere in Northern America.

    • @edwardolvera5280
      @edwardolvera5280 2 года назад +1

      @@lmcclymont mercedes-benz did it in a quarter of time Tesla did its.
      This weirdo does not know much about cars.

    • @edwardolvera5280
      @edwardolvera5280 2 года назад +1

      @@lmcclymont Mercedes-benz already took control of the EVs industry.
      And the faul lies in this weirdo who never could finish 100% the Self-driving autopilot.
      Thats why the company Tesla can not really take off.

    • @lmcclymont
      @lmcclymont 2 года назад

      @@edwardolvera5280 I gar unter you that FSD beta can work hands free at every single place the Merc can and then at millions of other places as well. You have zero understanding of what is happening here.

    • @lmcclymont
      @lmcclymont 2 года назад

      @@edwardolvera5280 umm L3 on a handful of roads is not full self driving 🤦‍♀️. Maybe read something other than the New York post or other FUD and you will understand the difference.

  • @mahdiamrollahi8456
    @mahdiamrollahi8456 2 года назад

    🥵🥵🥵 How fast you can talk ?!

  • @ericschoeman6613
    @ericschoeman6613 3 года назад

    This is old

  • @theSpicyHam
    @theSpicyHam Год назад

    (lol) weak techs (taunt)

  • @slightlygruff
    @slightlygruff 3 года назад

    Kachinski here will fail

  • @slightlygruff
    @slightlygruff 3 года назад

    Elon, quit worrying! we know you're an impostor but we will still love you just like your dad does