Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Scenarios in which Tesla FSD Beta 9.0 fails

twitter.com

Post reply on HN
Print view View original

41–50 of 502 posts

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#41

Post by throwaway0a5e »

wedn3sday wrote: post #28

I watched a human driver in a BMW weave at 90 mph through traffic yesterday, swerving back and forth between lanes inches from other peoples cars. If Tesla can make a car that's even 1% less dangerous than human drivers, that could be thousands of deaths avoided every year. Humans should not be allowed to drive cars on public streets.

The fact that a presumably average or not too far from average human can "weave at 90 mph through traffic yesterday, swerving back and forth between lanes inches from other peoples cars" should tell you how wide of a gulf there is between human operators and current FSD tech, which will dodge road debris only if it looks like a car, person, cyclist or traffic cone.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#42

Post by darknavi »

wedn3sday wrote: post #28

I watched a human driver in a BMW weave at 90 mph through traffic yesterday, swerving back and forth between lanes inches from other peoples cars. If Tesla can make a car that's even 1% less dangerous than human drivers, that could be thousands of deaths avoided every year. Humans should not be allowed to drive cars on public streets.

It will be interesting where we draw the line on "good enough".

I think people will naturally be much more critical of a car than human drivers even if "overall" they are statistically safer.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#43

Post by darknavi »

mrRandomGuy wrote: post #24
zyang wrote: post #16

It appears Tesla FSD just ignores things it doesn't understand, which is really dangerous in a production vehicle.

Why are you getting down-voted? There's literal videos depicting what you state. Is the Musk Fanboy Brigade behind this?

You guys can downvote?!

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#44

Post by darknavi »

verelo wrote: post #32
nrjames wrote: post #8

Earlier quoted context omitted.

I used to work with the USG. There was "Beta" software absolutely everywhere, including on some very sensitive systems, because it was not required to go through security approval until it was out of Beta. In some instances, these applications had been in place for > 10 years. That was a number of years ago, so I hope the situation has changed. In general, the USG doesn't have sophisticated infrastructure and policy…

USG? I'm not sure what that means, i did a google search and i assume it's not "United States Gypsum" or the University System or Georgia...?

US government I assume.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#45

Post by Syonyk »

stsmwg wrote: post #29

One of the questions I've repeatedly had regarding FSD (and Tesla's approach in particular) is the notion of memory. While a lot of these scenarios are disturbing, I've seen people wavering on lanes, exits and attempting to turn the wrong way onto one-way streets. People have memory, however. If we go through the same confusing intersection a few times, we'll learn how to deal with that specific intersection. It seem…

This has been a common assertion about Tesla's "leadership" in the field - that they can learn from all the cars, push updates, and obviously not have to experience the same issue repeatedly.

It's far from clear, in practice, if they're actually doing this. If they have, it would have to be fairly recent, because the list of "Oh, yeah, Autopilot always screws up at this highway split..." is more or less endless.

GM's Supercruise relies on fairly solid maps of the areas of operation (mostly limited access highways), so it has an understanding of "what should be there" it can work off and it seems to handle the mapped areas competently.

But the problem here is that the learning requires humans taking over, and telling the automation, "No, you're wrong." And then being able to distill that into something useful for other cars - because the human who took over may not have really done the correct thing, just the "Oh FFS, this car is being stupid, no, THAT lane!" thing.

And FSD doesn't get that kind of feedback anyway. It's only with a human in the loop that you can learn from how humans handle stuff.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#46

Post by throwaway0a5e »

tshaddox wrote: post #30
ethbr0 wrote: post #9

Earlier quoted context omitted.

Safely operating a motor vehicle via a steering wheel, accelerator, and brake (and sometimes clutch and gearshift) is a completely different skillset than monitoring an automated system in realtime. Novel skill requirements include: interpreting FSD UI, anticipating common errors, recognizing intent behind FSD actions, & remaining vigilant even during periods of autonomous success.

No, it’s just unsafe (and presumably illegal in most places) to operate a motor vehicle without maintaining constant awareness of the road and control of the vehicle. There’s no additional training or license that permits you to stop maintaining that awareness and control, just like there’s no additional training that permits you to drive under the influence of alcohol.

>There’s no additional training or license that permits you to stop maintaining that awareness and control

Being a cop on duty often exempts you from distracted driving laws.

I'm not sure how they can do stuff on a laptop while driving safely but I assume the state knows best. /s

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#47

Post by kemitche »

tshaddox wrote: post #30
ethbr0 wrote: post #9

Earlier quoted context omitted.

Safely operating a motor vehicle via a steering wheel, accelerator, and brake (and sometimes clutch and gearshift) is a completely different skillset than monitoring an automated system in realtime. Novel skill requirements include: interpreting FSD UI, anticipating common errors, recognizing intent behind FSD actions, & remaining vigilant even during periods of autonomous success.

No, it’s just unsafe (and presumably illegal in most places) to operate a motor vehicle without maintaining constant awareness of the road and control of the vehicle. There’s no additional training or license that permits you to stop maintaining that awareness and control, just like there’s no additional training that permits you to drive under the influence of alcohol.

The theoretical "additional license" would be in addition to maintaining awareness, not a substitution. So all the normal road awareness, plus being informed of likely FSD failure conditions, and anticipating them / being ready and capable to intercede.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#48

Post by Syonyk »

toomuchtodo wrote: post #35
Syonyk wrote: post #27

Earlier quoted context omitted.

Could have been equipment failure on the truck - a tie rod end failing or such will create some interesting behaviors. > I believe the argument is the software will improve to eventually be as good or better than humans, and I have a hard time not believing that. I find it easy to believe that software won't manage to deal well with all the weird things that reality can throw at a car, because we suck at software as…

Is flying a helicopter on Mars arrogance? Launching reusable space launch vehicles that boost back to the landing site arrogance? I don't believe so. These are engineering challenges to be surmounted, just as safe robotic vehicles are a challenge, and its reasonable (I'd argue) for us as a species to drive towards solutions (no pun intended). Silicon Valley isn't going to suddenly become less arrogant, but that doesn…

Aviation and space are a very, very different problem space from surface street navigation, because they rely, almost entirely, on "nothing else being there."

We've had good automation in aviation for decades. It doesn't handle anything else in the way very well at all, and while there's some traffic conflict avoidance stuff, it's a violent "Oh crap!" style response, nothing you actually want to get anywhere close to triggering. Automated approaches down to minimums require good equipment at the airport as well as on the airframe, and if there's a truck on the runway, well. Shouldn't have been there.

Same thing for landing boosters. There's nothing it really has to look at and understand that it can't easily get from some basic sensor data - speed, attitude, location, etc. It's an interesting challenge, certainly, but it's of a very different form from understanding all the weird stuff that happens in a complex, messy, uncontrolled 3D ground environment.

Self driving on a closed track is a perfectly well solved problem. Self driving in an open world is clearly very far from solved.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#49

Post by stsmwg »

Syonyk wrote: post #45
stsmwg wrote: post #29

One of the questions I've repeatedly had regarding FSD (and Tesla's approach in particular) is the notion of memory. While a lot of these scenarios are disturbing, I've seen people wavering on lanes, exits and attempting to turn the wrong way onto one-way streets. People have memory, however. If we go through the same confusing intersection a few times, we'll learn how to deal with that specific intersection. It seem…

This has been a common assertion about Tesla's "leadership" in the field - that they can learn from all the cars, push updates, and obviously not have to experience the same issue repeatedly. It's far from clear, in practice, if they're actually doing this. If they have, it would have to be fairly recent, because the list of "Oh, yeah, Autopilot always screws up at this highway split..." is more or less endless. GM's…

Great, thanks for that info. I'm remembering the fatal crash of a Tesla on 101 where the family said the guy driving had complained about the site of the accident before. It's interesting to know that there's at least a mental list of places like this even now. Disengagements should at least prompt a review of that interaction to try and understand why the human didn't like the driving. Though at Tesla's scale that has already become something that has to be automated itself.
Post reply on HN