The State of Tesla FSD (Late 2023)
Vložit
- čas přidán 28. 09. 2023
- Sponsored:
Use my special link www.privateinternetaccess.com... for an 83% discount, 4 months free and 30-day money-back guarantee on the best VPN - Private Internet Access
Version: 11.4.4 [2023.32.4]
Save up to $1000 on a Tesla & get 3 months of Full Self Driving for free by using my referral: ts.la/john27670
Consider supporting this channel on Patreon: / aidrivr - Věda a technologie
Maybe I need a flip off counter?
Sponsored:
Use my special link www.privateinternetaccess.com/AIDRIVR for an 83% discount, 4 months free and 30-day money-back guarantee on the best VPN - Private Internet Access
hi
what happened to your ai driver license plate?
@@reecejones1248 Need to get it transferred to the new Y! Could take a while, this is the California DMV we're talking about
You should take a road trip to the streets of Boston! Crazy roads and crazier drivers.
Nope, just report them to the police
Elon should have version 12 installed in your vehicle so we can have a great video presentation.
Yup!
Man i appreciate the effort you take for your videos so much!
Recording the center display and cropping each part out like the Indicators as well as speed, navigation and the text "creeping forward for visibility" just so you can put them in the bottom, as the Model S did! It looks so perfect. Actually had to check a few times if that really was the Model Y, because was so unsure. Well done!
It is so awesome to see your passion for what you do! Loving every video! Keep it up :D
I didn't know I wanted to watch entire FSD drives until I found your channel. Thank you for posting!
10:20 The car bailed and turned left because the road ahead LOOKS like a one way street. Proof the neural nets are actually working. It's actually impressive.
Been waiting for ur next video for so long! My favourite FSD review videos. Great work.
I'm suffering from ADHD, muscle spasms and sleeplessness. Your videos and especially the humor in your voice are so smoothing that I sometimes watch videos again just to smooth down. Maybe not the reason why you started that channel but for me the reason to watch it. 😄
Look up Dr. Eric berg on ADHD he gives knowledge on how to reverse ADHD.
Honestly always wait for your videos, you're great at shooting videos with music and good commentary keep it up
It's fascinating to see the progress. I remember not long ago most of the time it was being disengaged for going too fast, etc. and now it's down to these edge cases where it just needs a bit more assertiveness and nuance. Amazing to experience vicariously. Keep up the great work.
Were we watching the same video ?
Constantly using the wrong turn signals on normal roads are not edge cases.
Its still very far from perfect, but its vastly improved in a generally short amount of time@@michaelthomson5125
It's funny how tesla is supposed to be a tech car but BMW and Cadillac have better self driving ans auto Parking 😂
Neither BMW nor Cadillac have "self driving" cars. If you're referring to their highway driving assist, that is@@user-my4xu4gf1z
More FSD CZcamsr should use dark mode the visualisation looks so much better.
The turn signal problem is definitely worse than no turn signals. There has been so many times where my car has perversely signaled "right turn" because the road widens right before an intersection, but it is not actually going to turn. When there is a car waiting on the cross street they could reasonably take the signal at face value and start to go into my right of way. I usually quickly hit the stalk making it signal "left turn" making it (more safely) look like a crazy person is driving. I know I tend to believe other drivers more when they start their signal right before an intersection, so it's worrisome.
Every 6 months or so I check in to see how it's improving, I kinda feel like things are moving quite slowly, meaning 3-10 years until Tesla FSD is at human-like driving.
Calling it "generalized artificial intelligence" (1:25) is inaccurate. What separates these attention based models from generalized AI is its ability to exceed its training, i.e. the car starting to exhibit behaviors outside of the driving it has been trained to do. IMO that isn't desirable, but it bothers me a bit when people misuse this established terminology in order to overhype their tech on a certain social media platform. Side note - love your videos as somebody who doesn't want to drop the cash on FSD but loves to see this tech progress.
That is exacly wat happens with v12. It generalizes the training it has been given to navigate scenarios it hasn t encountered in his training.
@@lucadellasciucca967We will see whether V12 will stop for the construction-stop-sign dude holding out his hand.
It 100% will. It s just a matter of feeding the AI enough footage of it happening.
If a human can the AI will.
I really like how the visualizations are displayed, and the camera behind the car. This Model Y recording setup looks even better than the previous AI Driver Model S setup. With HW4, it will be interesting to see how FSD progresses on this channel.
Wow. The traffic there is nuts. The people parking all over the place making it barely a single lane is crazy. And OMG why so many people think it's OK to park immediately in front of a stop sign?! I couldn't live there. I would have a nervous breakdown.
Great video!!! It was definitely worth waiting. Cup of tea and big screen with AI DRIVR on ❤. All the details, like the disengagements counter and all other info on the screen is great.
18:00 I think that lady who flipped you off was mad you didnt pull to the side for a second so they could get unstuck😂
@20:43 I have the impression that it calculates a "pinch point" with the possibility of a parked car driver opening their door, so the path planning has to leave a few feet of room for that unlikely event. That may be why you're seeing hard braking for pinch points that would actually have plenty of room to drive through.
You continue to be the most informative and balanced FSD reviewer, hands down! FSD CZcamsrs are a dime a dozen, and the big names quickly trend to the uber bull / shill end of the spectrum. But you present a balanced view, and a deeper technical view. Finally someone discussing the end of the occupancy network, and the language token routing model shown at the last AI day. I suspect you have a tech background, plus high EQ, leading to a really good perspective for a reviewer of this tech. v12 is truly a big change, and it terrifies me how much is thrown away in the process, but has huge promise at the same time. I can't wait for you to get your hands on it!
Very perceptive about the camera resolution upgrade on HW3 cars to aid in HW4 training. Great content!
Always a treat when you uplaod!
Winter is coming on in NW Wisconsin. FSD has, thus far, been totally unacceptable as soon as the snow falls. I'm doubting that I'll trust it this winter because the car does not completely brake before going into turns. Doing so is absolutely critical in the snow and important, but not as much so, in wet weather.
Dude, the SPEED with which I clicked on this thumbnail. I dunno why but I really love AI Drivr’s content
Once again he revealed his "face" like Master Chief in Halo: Combat Evolved. Love it.
To my understanding, Occupancy network is just a part of vision model, it is a neural net system, and it is still there in v12. v12 mostly replaces the control part from manual code to net, and it's now all net, and can be trained end to end, which is huge. anyway, great video!
Is the control neural net in v12 making decisions from vector space data? Or directly from video footage? If it's using video footage, does that mean it's replaced the vision system?
@@spiderbite7849 I don't totally understand what you've asked, but (as a computer guy) I might be able to clarify that the v12 system uses video footage as its training input rather than hard coded rules (i.e. If -this happens- then -do such and such-.). So they thrown out those rules that are in v11 and given the machine learning algorithm oodles of examples of good driving behavior in the hopes it will generalize and generate the right "rules" on its own. The drawback is you don't really know how it's going to apply its learning/decisions until it has been presented with a novel or new situation. The drawback is also an advantage as it's more likely to respond after the fashion of the great examples it has been given (i.e. better than the average driver would respond). Neither the hard coded rules or the oodles of examples can anticipate all situations. If the machine learning screws up, you give it more examples of the specific behavior you'd like. It's similar to trusting a person to make decisions based on their experience versus writing a law for every situation they might encounter, if the person's experience was limited to only having done the "right" thing in the experiences they have had.
Ok thank you, I understand that v12 using a neural net to make desicions. But I'm confused as to why it's trained on raw video data, and not on the 3D vector space visulisation. So previously v11 used a vision neural net for recognising objects and placing them in 3D vector space space. Once everything was in vector space, the decisions were made from hard coded rules. But now, it seems v12 skips the object recognition vision>vector space part. If v12 runs a red light, how do we know if if vision failed or if control failed. In other words, did it not detect the red light (due to rain, haze, angle) or did it detect the red light, but failed in it's decision (due to insufficient training). In V11 this is easy to distinguish, but if v12 is video data in and controls out, I am not sure if this can be distinguished anymore. @@carabaoboy
@@carabaoboybut I think it is still doing steps for it's training. When those super computers get the video they still do all the labeling and occupancy network and then train the behave on that "translated" world.
@@Blanka-999 No labeling at all actaully. On that i m sure. The occupancy network i still have doubts but i m pretty sure that s gone too.
The person that animated that transitioned from one helmet to the other is amazing, That was fantastic work!
AI? 😁
@@jsjs6751 :)
About the turn signal - maybe it has code in it that obeys the law of turning the signal on 100ft before turning
Thanks for another great video. Your FSD visualizations are the best.
9:48 - my car does this on FSD beta 11.4.4 sometimes. When I end a trip it will see a parked car and alert me to take over thinking the car is headed toward me. Engages auto steer and alerts.
I'm really looking forward to V12. My current version is still great on highways and low traffic situations, but deep in the city is frightening!
Regarding the stop sign at 17:15. I don't actually think the software registers an upside down stop sign as a stop sign. If you look at applications that do facial recognition, they usually fail if you flip the camera upside down, as they don't actually understand concepts such as faces, only patterns such as eye, nose, ear, and mouth placements.
on of my favourite series on youtube!
v12 is not fully end to end. just all neural nets but not just one neural net. i know this because in elons v12 stream the visualization was showing.
I don't know more than you, but the visualisation could maybe run in the shadow mode, just to provide some display?
@@jsjs6751 hardware 3 has not the computer available to run multiple fsd instances
@@chickenp7038 If that is true, then ouch... Tesla may have a problem.
@@jsjs6751 well you only need to run one instance but if they go fully end to end they won’t have a visualization
Communities are making laws that you have to put on your turn signals at least 300ft before your turn. If laws like that are part of FSD it can cause confusion in managing turn signals.
@20:20 look at the red leaves just above the top of the red truck... it does kind of look like there is a stop sign behind leaves there (just barely). Just speculating on why the car stopped. Interesting that it didn't show a stop sign on its display.
There must be some benefit for Tesla and AI V12 team to keep releasing V11 versions, so yes please keep recording more videos on 11. It’s still very interesting to watch what changes. Also showing the differences to HW3 and 4. Maybe at some point you’ll say, now its better.
Maybe the updates are for a version 12 running in hidden shadow mode? 😋
One thing to note with the indicator signals is: what if the neural net is learning from successful indicators from other vehicles in order to validate responses
Here in Missouri, we have LOTS of roundabouts, and I have to disable FSD when I enter them.
I have HW3 and I don't think the processor has the horsepower to handle 2 lane roundabouts
it slows down, and folks honk at me and have LOTS of trouble figuring out if the oncoming traffic is going straight through or following the circle - I've been in many crashes where it guessed wrong.
It just is too slow to figure out what the traffic is doing.
I would say you should have a counter for improper signal use but that count would be pretty high. It would be nice to see how that has improved.
Looking at that bailed intersection I noticed that STOP seems to have been written in the middle of the road which it may have understood as it being a one way road and may have bailed to avoid oncoming traffic.
Can you track disengagements and show us a graph of the improvement of them
so nice to watch this. pure pleasure. i don't know why, but, have subscribed!
LOL dat helmet bait was great. On other notes, as always nice video thanks for the content!
Correct me if I'm wrong but I don't think they're getting rid of all the occupancy networks and stuff they did before on perception, the only thing they're replacing now is control which was the remaining coded stuff. I'm pretty sure the old perception networks are still in there but now just able to be trained end to end with the rest of the model
They can probably also be improved upon, since there is so much compute overhead available now that the hardcoded stuff is gone
I was kind of thinking the same for the occupancy netwrok but then again we know there is no more lebeling happening. The car doesn t know what a stop sign is in v12, or a round about etc. If that is the case, and it is, then why have the occupancy network. The car will learn from the video training what is drivable space and what is not.
@@lucadellasciucca967 the occupancy network also helps with just knowing if there is an object in the space, even if it is not recognized. Presumably v12 will understand “don’t hit stuff” but maybe the occupancy network will still be needed
@@SyntheticSpy it s definitely possible
Interesting, as someone who lives in the UK it is nice to see people use full self driving on roads like this which are a lot more similar to the roads I drive on. Most videos seem to be on big wide American roads which we don't have much off here, which has always let me to be more of a self driving sceptic, but it handled some of the complex situations fairly well.
Tesla's "Autopilot" will never become available in Europe as it's technology fails even the lowest safety-expectations. A system that is SOLEY based on cameras will never achieve a statisfying reliability. It doesn't matter what the algorythms and 'AI' do with the data from the cameras since this data is inherently extremely unreliable.
If Musk ever wants to sell "self driving" cars in Europe, it is absolute ESSENTIAL that he scraps his "LIDAR bad, Cameras good" attitude. Without a multitude of sensors that must either confirm or deny the cameras interpretation of information, self-driving will stay an american thing. Which I'm quite thankfull for. I have zero interest in sharing the street with a bunch of self-driving cars that rely solely on notoriously terrible video and picture interpretation, which can't even correctly distinguish between colors on a mildly sunny day.
Nooo thanks!
The direct recording of the screen, especially the way you overlay it onto the main camera footage, is da bomb.
My two biggest problems with 11.4.7 has been the random stops during turns, or at random times. Not sure why this happens but its very frustrating and happens a lot, but i report each one. and then the problem with the windshield wipers going off even when there's no rain....that's extremely annoying also. i hope they fix that quick.
And lots of unnecessary wiper action on cloudy days
@@darrylnix2582 I think it's trying to communicate with us. Have you recorded the wiper signals and tried to decipher?
We are in Barcelona right now. European cities are 10x more challenging than even the most difficult bay area roads where I live...
That's true, but also the great thing about European cities is you don't have to drive everywhere.
I have watched other self driving videos and yours are the highest quality.
Awesome! I’m in Claremont Canyon and have always wondered how FSD would do up here
Until v12 lands, in about "two weeks..." lol, I think it could be very instructive to see a video of a hardware 3 car and a hardware 4 car doing the exact same route. Keep up the good work! Love the videos.
Welcome back!
12:27 love how it's not using the turn signal here, where it would be necessary. :D
It's always impressive what the system can do.
And by us it can't even recognize speed signs❗️😴
Greetings from Switzerland.
Yeah in Switzerland you just have access to Autopilot not FSD.
Welcome back! For about 2 months I've seen dirtytesla FSD videos in my recommended and got excited it was you, but alas, no. I didn't drink that off brand diet coke though, I stayed faithful
Haha this made me chuckle. DirtyTesla is a great channel!
I think that's why Tesla deleted the stalk and moved the turn signal buttons to the steering wheel, to bring human signalling in line with v11 signalling. :)
May I just say that is so cool that the car applied emergency steering when you were going into the curb @ 9:41
Okay, so I think interactions like stopping at a stop sign for constructions will work properly in v12.. I do think the Honda driver flipping the bird to you was very unnecessary since she nearly literally crashed into you 😂
I'm really glad you're back making these videos with your new hardware! You deserve more views for sure. People NEED to see what AI driving can actually do. We need more acceptance of this technology as soon as possible - it will save lives. Even though it still behaves way too much like a beginner in their first driving lesson lol
Did you trade in yer ms for the my and take advantage of the fsd transfer, or just get the my and transfer the fsd?
Good job as always!
Is it common in the US to have two dudes holding signs for a living at these kinds of road work? 15:25
I wouldn't worry about it taking a long time to train HW4, once Tesla figures out the most efficient way to do it with HW3 + they will have way way more computing power by then, training HW4 will happen very quickly
I think that when they have more compute power they will increase the data set, to the point of maxing out the available compute power. That is, I expect they will always choose bigger computation, for the purpose of capability, rather than having the compute process take less time.
Yea, probably a couple of months. Musk months🙂.
@@cleon_teunissen yeah but why did HW3 take such a long time to compute?
It wasn't that they were lacking data.
They didn't have the computing power and they also didn't know how to make the AI algorithms, now that they do have the computing power with Dojo and they know the code cause HW3, HW4 should come quicker than people expect
@@cleon_teunissen good point though I do think they also will do that
@cleonteunissen7761 I agree. But they could also save electricity/power using a smaller set, both during the training and in the car.
Regarding not blinking BMWs: in Bavaria a saying goes ‘I know where I want to go and where I want to go is nobody else’s business’
I also raised my speed limit input on my hardware 4 version 11.4.4. I’m pretty happy with it but it still gets Squirrley from time to time.
What camera setup are you using for the outside view?
Nice one again. Good job. Can't wait for v12
I don't think they abandoned the occupancy network and other neural nets in FSD 12. They just added more neural nets in place of handwritten logic.
Like in human brain, there are specialized structures for specific tasks - not all neurons are the same.
The info I'm seeing is that v12 is end-to-end, one NN. Photons in, vehicle controls out. There will likely continue to be a separate (V11) perception neural net onboard for the on-screen visualizations.
Dude, love your vids :)
If Tesla are purely relying on NN for both HW3 and HW4, it makes sense to me that they would “normalise” both sets of incoming data (that is colour correction and upscaling/downscaling) prior to training and executing on NN, otherwise they are going to need two sets of NN. I think after awhile, they will take advantage of the better hardware over time, but it’ll be lowest common denominator at the start to they to have a smoother transition
How do you switch off the notifications where FSD would require for you to move the wheel?
Great video.
About the model 3 event, I think it made the right decision because if you look back, there was enough room for the model 3 to pull to the right or left, if it was going to pass, but as it was going to turn right, the M3 went wide instead of a passing spot. As for the model Y scenario issue, I think the model Y maybe should have waited for traffic to pass before conducting an almost 3 point turn in a intersection with 3 cars entering it. I think most normally people would wait. It almost caused a dead lick scenario.
Great! Very informative and entertaining!
Great video and narration
Excellent video!!!
the 10:20 crossroad turning left is probably due to NTHSA's regulated rule hardwired to force going in the direction of your marked lane. I bet you were on the "left turning" lane
10:20 my assumption is that it "thinks" it should never make a right turn across the path of another vehicle (the one parked at the stop sign)
Thank you!
Great analysis as always.
i get a lot of emergency autosteer if i'm stopped (at D) in the middle of the road and restart driving (i don't have FSD).
Some people make a fetish out of putting their turn signals on early. Turning your indicator on two or more intersections before you turn is nuts and yet people swear by it. I don't understand some people.
They're no nuts, they're wrong.
Yeah, and some does it too late... or never.
Just remember why we're supposed to use them: we show what we're *thinking* about doing, so that our fellow road users can act if we do do not act correctly. You know; for safety.
The earlier we can show our planning in an unambiguous (!) manner, the more time they have to use that information.
Also, it's good for efficiency.
But yes, the signalling should not leave any doubt as to what you're thinking about doing, so don't do it before it is unambiguous.
You do a great job,thx,man!
2 prius in the same minute of video for a total of 3 in one parking lot. more than I could keep count of by the end of the video. Can't wait to see how much better this gets!!
17:46 was the white car's fault for stopping the the middle of the road so that the blue car couldn't turn in, yet they get irritated and flip the bird 🙄
As to vs 12. I'm not understanding... are the images for reference fo vs12 residing in the computer in the car? They can't be in the cloud, too slow to respond. But how much storage do you need to put them in the system in the car given there are millions of miles of reference images! ???
So in Australia we don't have fsd beta, however the autopilot and cruise control did get updated with more colourful camera feeds and it has actually made the experience worse for some reason, lots more phantom braking and weird bugs all around, I had to stop using it.
Please keep Producing. your videos are by far the most Pro and convincing to the uneducated.
What version are you running?
4:36 very little difference in resolution. What's the reasoning behind the change?
Inappropriate use of turn signals and how it handles round-abouts will be things to test thoroughly with V12.
how long can you be hands off before it tells you to put your hand back on the wheel? on the new Lexus, if I have my hands off for even for just a few seconds, it beeps like crazy!
Do we know if the visualizations from V11 will be carried over to V12, or will visualizations also be based on end-to-end NN? I guess the purpose of the visuals is to show the passenger what the car can and can't see, so in theory it should be using the new video-trained networks?
I was impressed that it maneuvered the round about. Ivermectin been waiting to see if a self driving car can do that since I myself have trouble with them. Very impressive I’d almost want one just for this reason.
Are those camera specs correct? As the resolution would be exactly the same pretty much
im not a tesla engineer or something but my guess is that the visualization is being generated from an object classification ai but the driving ai gets the classified object data with the occupancy networks output. while object classification can give more false positives or just doesnt get it, occupancy network does a better job at defining if the road is obstructed consistently. the gray thing you see on the road edges or in roundabouts, is the occupancy network showing that car knows it cant drive there
I am new to the channel! I have a question How is the phantom braking issue? While on FSD?
I faced twice while on autopilot, scared the shit out of me. Never used auto pilot again. So I am super scared about fsd
But … without the occupancy network how will the park sensors work?
I can see the car learning to park in all kinds of situations just by video training.
My observation with 3 car is turn signal coming on when passing turn lane, also when enteringb a vnew roundabout it has no clue, finally on 2 lane highway the car does not know what to do with passing lane
Glad you're back! If Optimus was driving someone around, Optimus would have to have insurance (paid for by Tesla, unless he had his own back account). And I can't wait to see your v12 videos... they will be the best!
Nice to see a new post. Thanks! Did you trade/sell your Model S to get the Model 3 or do you still have it? Pretty cool to see a drive with FSD beta using HW4. It's the first one I've seen. As for the v12 version of FSD beta, I can't wait but since it's only in early alpha release now, I'm not going to hold my breath about seeing it before sometime in 2024. Hopefully earlier in the year than later.
I hope the new version is much better with signals. As a general rule of thumb, you should almost never be moving in the opposite direction to your signal, yet it does that with alarming frequency. Tesla needs to learn a bad signal is far worse than no signal at all.