Search results

Human brain requires far fewer examples to learn and is better suited to processing video information than current generation of computers. And it does it at a fraction of the energy. It's been nearly two years since USS have been ditched and the car still cannot park itself, something that...

I wonder how many of them knew they were only buying a "door to door" L2.

So if we were drunk then police would still write us up, right? How much more would people then pay for such an L4 that is legally an L2? And again, who will license such a solution from Tesla?

I wonder what they do after another two-three years down the road they throw in the towel on their Vision only attempt to get them to an L4/L5 (probably even an L3)? Do they ditch the robotaxi stuff and will be overtaken by the Merks and Bimmers as premium EVs with L3 or L4/L5? And won't be...

Well, they tell which humans are and are not allowed to drive, set speed limits etc. Cruise couldn't test before they convinced the regulators that it's safe enough to do so. And they are not allowed to operate them as robotaxis as a result of what happened. Which is why this whole SAE system...

As was discussed earlier in this forum, all this S4-S5 stuff is a bit beyond the point, it's subjective manufacturer's opinion of what their car can do. What really matters is what the regulators allow. Waymo is allowed to operate in fog. Tesla, as long as they continue to double down on...

So Tesla can identify as an L5 but it won't mean much in reality because as long as the CA DMV is unhappy with the technology it won't be able to deploy robotaxis in California. In this case I think the bet between spacecoin and Joey D needs to be modified. It's not what Tesla calls itself...

I suppose 2) will not arrive before 1) in any case. And L3 will have to arrive before that. Also, I am not sure it's for Tesla to declare itself an L4 or L5, it will be up to the regulators. So I think my original point is correct then. Tesla needs to be an L5 for its version of robotaxi...

Quoting from diplomat's post: L4 is designed to perform all driving tasks and fallback on its own but only in an artificially limited ODD. L5 is designed to perform all driving tasks and the fallback on its own in a wide ODD of a typical human driver (ie everywhere, day, night, all drivable...

This is precisely what I thought, and this is why I think a Tesla robotaxi needs to be an L5 while Waymo only needs to achieve an L4 in a geofenced area. Waymo is basically there already while Tesla is, well, an L2...

London is 25% of all taxis in England and Wales. So my guess is large cities are probably around 70% of all demand for this kind of technology. Maybe this will be just enough for Waymo? Why are you focusing on Tesla reaching the L4 level? L4 is enough for Waymo because they are happy to stay...

It should all be fixed in the next four months. Or there will be no robotaxis in SF, only in little suburb towns like yours.

So I am not missing anything then. This is crazy..

Does anybody here understand the logic? One would think an L4 robotaxi is a natural bet if your existing cars are already L3 and there's reasonable expectation that you have the technology to get to an L4 in the near future. But this is not where Tesla is right now, not even in the ballpark...

And.. Waymo has cameras at the front of the car, something that in my opinion is crucial but gets continuously voted down by the fanboys in the F12 forum. LIke, can't keep them clean or some other nonsense like this. And it's Tesla, not Waymo, that relies exclusively on cameras. Go figure..

Agree, and I think some of those other bits are important for the reason that doesn't get mentioned enough. Humans are vastly superior at processing video information than the best computers, for now. Both better and requiring much less energy. Which is why if you can offload some of the...

Waymo uses radar and lidars, Tesla only vision. Maybe this is the answer.

It will be a Robotaxi (Supervised) car rental service. Just another brand name, just like the FSD (Supervised) autopilot.

Mercedes used headlamp wipers years ago.. Doesn't feel like its the kind of problem that Tesla guys wouldn't be able to solve if they wanted to. It's just that it feels like 1/3 of complaints in this forum are about front visibility, and there's only one solution really, and that's to have...

Has there been definitive conclusion why a car that relies solely on vision does not have camera(s) at the front? Other than not to piss off the HW3 guys? Is it somehow easier to make the vision technology more portable (and so easier to license out) if the cameras are relatively close to each...

Oh mate, it's tough to argue when the other side's goalposts are constantly shifting. So this thread is basically just about an autopilot? If you admit that all those L4 and L5 claims are no longer in the picture then it means that all those who doubted that vision only L4 and L5 will not be...

Mostly because robotaxis are not touted anymore, and instead it's now this Supervised Full Self Driving, which is a word soup. If Elon still believed he can pull off FSD with just vision he'd continue making those claims. It was discussed a million times how humans have stereo vision, and can...

Supervised Full Self Driving is an oxymoron, like, for example, "organized chaos" :)

Then what does "F" in FSD stand for? Supervised Full Self Driving is an oxymoron, isn't it? That's the point I was making. It looks like with vision only you are achieving a glorified autopilot. For Full Self Driving, you probably need more than just vision. And that is what the discussion...

The fact that Musk now stresses "supervised" FSD kind of refutes your claim. Supervised FSD is not really FSD, is it?

Best part is it will soon be two years since they've ditched the USS. And as it is pretty clear now, they didn't even have a hint of a working vision based prototype at the time. A bunch of cowboys..

More like horrible design error. Blind spot (no camera(s) in front) + no ultrasonic sensors + the car cannot map reliably what it saw a second ago.

05:20

It's the Tesla customers that are the problem. They are buying, time after time, into the promises that don't materialise. As long as they do there's no incentive to deliver, just feed them another amazing single stack mumbo jumbo in two weeks and they will stay happy for while.

https://www.notateslaapp.com/news/1831/tesla-autopilot-director-talks-about-the-future-of-high-fidelity-park-assist-and-it-coming-to-vehicles-with-uss "First, the bad news. The new technology is initially available only to customers with Tesla models that do not have ultrasonic sensors." How...

Or simply that Tesla's automatic collision prevention systems (those relying on vision only) are not adequate enough - especially once you control for the fact that it's a much more fun car to drive than a Ram. Honestly I wouldn't read much into this. You can't compare accident rate between a...

Point is that a much older Model S that he brings out around minute 20 is just as good as these newer cars.

I can tell you for a fact that this is not the case for all car manufacturers. And in fact Tesla was very much up there with the rest of them up until recently: Check out 20:00 when he gives up on a recent M3 and tries his old Model S. So no, the sensors are not mixed at best. They are...

A lot of stuff we don't know but the one thing we do is that the car could self-park when it was shipping with USS and cannot do it now (I've posted a couple of times on this, won't do it again now). I get it that self-driving has never been done before, and it will be super impressive if Tesla...

Does anybody understand why Teslas don't have cameras in the front of the car? Especially after the USS were deleted, but even when those were still there, seems like an obvious omission for a car that bets so much on Vision.

Depends on your definition for real FSD. If you want a car that will never get into accidents (as somebody at Tesla claimed) that could be prevented with better placed cameras or radar(s) (like creeping into intersections) or a car that parks itself (as you claimed a year ago), then current...

Tesla is obviously missing a camera in the front of the car, without it there's no hope of self parking or 360 view or adequate visibility in intersections. No amount of software updates can compensate for that.

I think a better approach is to leave it to the private sector. Require an FSD car to record and report who was in command when an accident happens (this will be a requirement under the new UK law anyway), and let insurance companies decide what your premium should be depending on whether you...

From today's King's speech (this is how the UK government outlines legislative acts that are planned for the upcoming parliamentary session): https://europe.autonews.com/automakers/uk-make-self-driving-car-makers-liable-incidents

When Tesla reports that the FSD is x times better than a human, how do they compile the numbers? This is an honest question. If a human is obsessively watching over the FSD, this by itself should make the drive safer, no?

I think a more realistic scenario is insurance companies starting to offer policies where your no claim bonus is not affected if the car gets into an accident while in FSD mode. In fact, since Teslas FSD is 5 times safer than humans they should be doing it already. I guess there is currently...

The tweet is just marketing. "It’s going to be very hard to beat it with anything else!" Why? Parking solutions with no neural networks but with USS are still beating Vision hands down, a full year after the decision was made to ditch the USS, so no proof so far that even this trivial task of...

As the latest Pixel 8 Pro shows, AI can only take you so far without proper hardware.

Full year after the decision was made to ditch the USS sensors:

As the video mentions, this is not the first time Tesla fails to recognize an emergency vehicle. And then there is another infamous video where it fails to recognize a child mannequin, and a video from the UK where the car refuses to see a red garbage bin that's right in front of it, and I am...

Wouldn't have happened if the car still relied on a radar..

I thought the idea of ditching the radar and the USS was that they don't integrate well with the Vision so each time there are new models of the sensors it would require the whole system to be re-trained: Of course, the question of why you need to integrate a radar into Vision at all...

Was told to choose between his duties as an air traffic controller and a Tesla blogger?

This is one of the few cases where the EU regulations make sense. FSD is a work in progress, let them sort it out in the US first and then move on to adapting it to Europe and other places. One step at a time.

It means there will be an objective way to tell if the car was in autonomous driving mode when the accident happened, and so the insurance can recoup its losses from the manufacturer if the car was at fault. It makes it the responsibility of the manufacturer whether to allow the driver to not...