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

91–100 of 502 posts

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#91

Post by misiti3780 »

SloopJon wrote: post #86
nikhizzle wrote: post #3

Does anyone have any insight as to why regulators allow a beta like this on the road with drivers who are not trained to specifically respond to it's mistakes? IMHO this puts everybody and their children at risk so Tesla can beta test earlier, but I would love to corrected.

The Twitter thread is lacking in attributions, but I saw most of these some months back after a post about scary FSD behavior. I watched with morbid curiosity, and a rising level of anger. The guy with the white ball cap repeatedly attempted a left turn across two lanes of fast-moving traffic, with a drone providing overhead views. He seemed smart, aware, and even a bit conservative in intervening. Nonetheless, I cou…

How do you know the beta drivers did not get training?

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#92

Post by bobsomers »

serverholic wrote: post #72
Syonyk wrote: post #11

I don't understand how something this broken is allowed to operate on public roads. If I drove like Tesla's FSD seems to based on the videos I've seen, I'd be pulled out of my car and arrested on (well founded) suspicions of "driving while hammered." After a decade of work, it's not capable of doing much beyond "blundering around a city mostly without hitting stuff, but pay attention, because it'll try to hit the mos…

We are going to need a fundamental breakthrough in AI to achieve the level of FSD that people expect. Like a convolutional neural network level breakthrough.

I don't think that's necessarily true. There are plenty of people in the AV space that routinely drive significantly better than this and are already doing completely driverless service in some geofences.

The problem with Tesla's approach has always been that Elon wanted to sell it before he actually knew anything about how to solve it. It's lead to series of compounding errors in Tesla's approach to AVs.

The vehicle's sensor suite is woefully inadequate and its compute (yes, even with the fancy Tesla chip) is woefully underpowered... all because Elon never really pushed to figure out where the boundary of the problem was. They started with lane-keeping on highways where everything is easy and pre-sold a "full self-driving" software update with absolutely no roadmap to get there.

To overcome the poor sensor suite and anemic compute, they've boxed themselves into having to invent AGI to solve the problem. Everyone else in the space has happily chosen to spend more on sensors and compute to make the problem computationally tractable, because those things will easily get cheaper over time.

I'm fairly convinced that if Tesla wants to ship true FSD within the next decade, the necessary sensor and compute retrofit would nearly bankrupt the company. The only way out is likely to slowly move the goal posts within the legalese to make FSD just a fancy Level 2 driver assist and claim that's always what it was meant to be.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#93

Post by moralestapia »

Syonyk wrote: post #11

I don't understand how something this broken is allowed to operate on public roads. If I drove like Tesla's FSD seems to based on the videos I've seen, I'd be pulled out of my car and arrested on (well founded) suspicions of "driving while hammered." After a decade of work, it's not capable of doing much beyond "blundering around a city mostly without hitting stuff, but pay attention, because it'll try to hit the mos…

Because Elon doesn't operate under the same jurisdiction as us common people.

Try calling out a random diver a 'pedo', or perform the most cynical kind of market manipulation (then laughing to the SEC at their face) and your outcome will be very different.

It's Animal Farm all over.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#94

Post by timroman »

sidewndr46 wrote: post #37
croes wrote: post #4

I doubt that autonomous driving will work in the next couple of years without infrastructure adjustments. We built roads for cars to replace horses, we will need to built roads for autonmous cars to replace human driven cars.

If we're going to build what amounts to new infrastructure, shouldn't we build transportation infrastructure that does away with the need to own cars? At least for transport in urban and suburban areas.

IMHO they're the same thing. Automate all cars to get around the right of way and high construction costs that limit rail development. I think the upgrades needed to roads are minimal in comparison. Maybe some sensors and signals but it may be just perfecting signage, lines, etc.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#95

Post by wanderer2323 »

Geee wrote: post #65

It seems to estimate the surroundings pretty well in the new version, but the path planner still has issues. I'm not sure if they already do this, but I think Tesla should run FSD on all cars in shadow mode, and then use the FSD vector data and driver actions to train the path planner. Basically using FSD vector data as input and driver actions as output of the neural net. If the network can't reach confidence in cer…

> seems to estimate the surroundings well

> repeatedly tries to drive into the monorail pillars

Choose one and only one

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#96

Post by specialist »

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…

My thoughts exactly. I've made those mistakes myself, many times.

I guess I sort of assumed that Tesla would do three things:

- Record the IRL decisions of 100k drivers.

- Running FSD in the background, compare FSD decisions with those IRL decisions. Forward all deltas to the mothership for further analysis.

- Some kind of boid, herd behavior. If all the other cars drive around the monorail column, or going one direction on a one way roadway, to follow suit.

To your point, there should probably also be some sort of geolocated decision memory. eg When at this intersection, remember that X times we ultimately did this action.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#97

Post by visarga »

Syonyk wrote: post #71
Geee wrote: post #65

It seems to estimate the surroundings pretty well in the new version, but the path planner still has issues. I'm not sure if they already do this, but I think Tesla should run FSD on all cars in shadow mode, and then use the FSD vector data and driver actions to train the path planner. Basically using FSD vector data as input and driver actions as output of the neural net. If the network can't reach confidence in cer…

I've been hearing for years now that this is a Tesla advantage, that they can run in shadow mode, learn from humans, and big data learn all the quirks of the roads so they don't have to learn them in the self driving system. If this has been the case, evidence here is certainly lacking. Turning down a street one presumably hasn't seen a car drive down in this direction? Failing basic stationary obstacle avoidance bec…

It's a cherry picked set of examples you're drawing generalisations from. On any day I can see more reckless driving from humans than I've ever seen online with Tesla.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#98

Post by SloopJon »

misiti3780 wrote: post #91
SloopJon wrote: post #86

Earlier quoted context omitted.

The Twitter thread is lacking in attributions, but I saw most of these some months back after a post about scary FSD behavior. I watched with morbid curiosity, and a rising level of anger. The guy with the white ball cap repeatedly attempted a left turn across two lanes of fast-moving traffic, with a drone providing overhead views. He seemed smart, aware, and even a bit conservative in intervening. Nonetheless, I cou…

How do you know the beta drivers did not get training?

I said that they should. I don't know whether they do.

A March 2021 tweet indicated that beta access will be as simple as pressing a "Download Beta" button in the car. A subsequent tweet said that the program had 2,000 owners, some of whom have had their access revoked for not paying enough attention to the road.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#99

Post by lostmsu »

H8crilA wrote: post #25
moojah wrote: post #20

This really isn't beta grade software, as it isn't feature complete as the failure scenarios in the video clearly show. I'd call it alpha grade, and it has been that for a while. It's not 2 weeks or whatever unrealistic timeline away from being done, as Elon has claimed for ever. 2 perhaps years if we're lucky, but given human and driving complexity probably way more before even the whole of the USA is reliably suppo…

Like Donald Trump, but for nerds: http://elonmusk.today/ FSD would be equivalent to the Mexican border wall, I guess?

And the tax hike on cap gains.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#100

Post by tshaddox »

kemitche wrote: post #47
tshaddox wrote: post #30

Earlier quoted context omitted.

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.

If you maintain control at all times, you shouldn’t need additional training for any of the car’s features. We don’t require additional training for cruise control, lane-keep assistance, anti-lock brakes, etc.
Post reply on HN