Rate of progress really is exponential, especially if on the right track.I'm looking forward to v12.4 and beyond, but at this pace I fully expect L4 city-streets FSD to be at least a decade away.
You can install our site as a web app on your iOS device by utilizing the Add to Home Screen feature in Safari. Please see this thread for more details on this.
Note: This feature may not be available in some browsers.
Rate of progress really is exponential, especially if on the right track.I'm looking forward to v12.4 and beyond, but at this pace I fully expect L4 city-streets FSD to be at least a decade away.
60% done
I'm taking that into account. For L4 reliability, the car will need to be able to drive at least a million miles on average between necessary interventions (where the car makes a clear mistake that any skilled human driver would avoid). Right now it seems to require such an intervention about once a mile. That's six orders of magnitude improvement needed before it reaches L4, and progress will get more difficult as it gets into the long tail of unusual edge cases. (Many of the current failures are quite common cases, which actually makes it all the more puzzling why they haven't been solved.) Even if the reliability improves by an order of magnitude every two years [exponential improvement], which to me feels like an overly optimistic assessment, that's 12 years before it reaches L4 reliability.Rate of progress really is exponential, especially if on the right track.
No luck, I'm sitting in my car now. Oh well.Wake your car up. Charge it, open the doors, turn on ac...etc...
I haven't driven V12 yet, but in prior versions, whenever I noticed someone having a worse experience that everyone else isn't, the thread participants usually recommended recalibration of the cameras. Don't know if it will help, but it can't hurt.My first drive experience with 12.3 was similar. Even on the 'assertive' setting, it wanted to drive painfully slowly on unmarked two-lane roads, like less than half the posted speed. (Much slower than any reasonable human.) It double-stopped at most stop signs; first stopping far short of the stop line (where it couldn't see cross traffic), then lurching ahead to the stop line, stopping again to get a better view, then finally proceeding.
In a five-mile drive in good conditions, I had to intervene several times to avoid getting honked at. The car often didn't accept the right of way, including once where it pulled up to a 4-way intersection and the opposing driver was turning left. I got to the intersection a couple seconds before the other driver, so had the right of way, but the car didn't take it, so it became a standoff. But as soon as the opposing car lost their patience and started the turn, my car lurched forward, and the other car had to step on their brakes and honk.
A minute later, the car surprisingly got into a clearly-marked left-turn-only lane when it needed to go straight. I've never seen it make this mistake at this intersection before, so this was a regression. A bit later, it needed to cross two lanes to a median, but it stayed frozen for about 45 seconds, even though there was absolutely no cross traffic, and no apparent reason why it didn't go. Eventually another car did go by, and after that FSD proceeded across to the median. A few blocks later, it reached an intersection where the lane became double-width (unmarked), to allow cars on the left to go straight and cars on the right to turn right. The car hogged the center of the wide lane, making it ambiguous to drivers behind me what I was going to do. No good human driver would have done that.
Overall, not a noticeable improvement over v11, and perhaps a regression. I'm looking forward to v12.4 and beyond, but at this pace I fully expect L4 city-streets FSD to be at least a decade away.
I'm taking that into account. For L4 reliability, the car will need to be able to drive at least a million miles on average between necessary interventions (where the car makes a clear mistake that any skilled human driver would avoid). Right now it seems to require such an intervention about once a mile. That's six orders of magnitude improvement needed before it reaches L4, and progress will get more difficult as it gets into the long tail of unusual edge cases. (Many of the current failures are quite common cases, which actually makes it all the more puzzling why they haven't been solved.) Even if the reliability improves by an order of magnitude every two years [exponential improvement], which to me feels like an overly optimistic assessment, that's 12 years before it reaches L4 reliability.
I am eagerly awaiting your 1st impressions...While I wait for V12 to install, so I can take a worthless spin in the dark with no traffic (reminds me of 10.2 or whatever years ago), my thoughts:
1) It's very very nice to hear a bunch of positive reviews. Of course, we've had this in the past too, but I think overall reviews this time seem somewhat more positive than prior major releases' "first impressions." But I'm extremely jaded & bitter & an inchoate curmudgeon, and until I see v12 able to drive smoothly and stop for slowing traffic ahead without slamming the brakes unnecessarily, or enter a turn lane where it will have to come to a stop with just the right coast speed (a HUGE problem with v11), I'm still skeptical. I'll also be looking at basic residential streets and stop sign performance. These are basic every day things that have to be awesome.
2) Fully agreed on the vast gulf between where we're at and where this needs to be for anything approaching even L3 in actual useful ODDs. That's clear even without driving v12, based on all the videos people have provided.
3) RE your rate of improvement argument: I think the next couple months and the first release or two and how those go will be the real thing of interest. Specifically, it will be good to look at things that Tesla has said they are specifically working on and focusing on, like Chuck's left turn. The next release or two should incorporate a LOT of training for that case (Elon will tell us if it doesn't), so we should certainly see major improvements in success rate there very quickly (way beyond 9 out of 10, perhaps to 99/100 in the next release or two), if this NN training method is to actually be successful (with current hardware). Obviously on Chuck's other test case from his video today it should be very successful as well (rather than 0/3). If this improvement doesn't happen, there will have to be a really convincing explanation - otherwise we would have to assume that training just doesn't work as expected and doesn't actually provide a rapid improvement benefit.
In short, the next beer bet I should certainly lose, otherwise FSD v12 NN end-to-end with current hardware is probably doomed. Cheers.
Good idea, worth a try. The car is a 2017 Model 3, but I would have expected that miscalibrated cameras would have affected v11 as well? V12 is now downloading on my 2022 Model Y as well, we'll see if it's significantly different there too.I haven't driven V12 yet, but in prior versions, whenever I noticed someone having a worse experience that everyone else isn't, the thread participants usually recommended recalibration of the cameras. Don't know if it will help, but it can't hurt.
Wake your car up. Charge it, open the doors, turn on ac...etc...
No doubt they can improve specific common cases by explicitly bolstering the training set for those cases. The question is whether that approach might inadvertently underweight something else important, or also whether it will help at all the with the long tail of edge cases that don't fit neatly into any category. Their approach seems to be to feed the NN with millions examples of good driving, and ask it to mimic that behavior. But it's not clear whether they have a counterpoint mechanism of feeding it examples of things done _wrong_, and training it _not_ to do those things? (That's often how humans learn most effectively.) For example, it may simply not be "obvious" from the million "good" examples that double-stopping at stop signs is "bad", and this principle does seem to explain a lot of FSD's quirks and failure modes. There's also of course the question of whether the current hardware (HW4) is fundamentally adequate for L4, even with "perfect" software. (Will it need additional camera angles, or more/faster compute, or audio input, or ?)RE your rate of improvement argument: I think the next couple months and the first release or two and how those go will be the real thing of interest. Specifically, it will be good to look at things that Tesla has said they are specifically working on and focusing on, like Chuck's left turn. The next release or two should incorporate a LOT of training for that case (Elon will tell us if it doesn't), so we should certainly see major improvements in success rate there very quickly (way beyond 9 out of 10, perhaps to 99/100 in the next release or two), if this NN training method is to actually be successful (with current hardware).
Unfortunately, yes. Fsd branches have been screwed up since it started.So am I screwed if I’m somehow on 2024.2.7?
It was ok, but not great, and having zero traffic and darkness makes this report next to useless.I am eagerly awaiting your 1st impressions...
What? My car is Driverless all the time. Minnie Driver has never been in my car.12.3 drives very very well,
But you guys are right too, driverless still seems a long long way to go, especially for HW3
V12 is amazing ADAS, but...