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

381–390 of 502 posts

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#381

Post by cromwellian »

TheParkShark wrote: post #361
cromwellian wrote: post #355

Earlier quoted context omitted.

Because every year, Tesla keeps saying it's going to ship soon. It's clear this isn't even close to ready, I'd say it's 10 years from shipping, if not back to the drawing board. Tesla is having people pay for a self driving package as an option, and years later, it still isn't available. Shouldn't they refund their owners? I mean, just look at the visual representation of what the FSD is showing. It has no temporal s…

The visual representation isn’t an accurate measurement of what the car is actually seeing, I think Tesla cleaning this up (which is has on the newest FSD) will be a clear way to show people what it sees. I’d like to see Tesla do more to calm doubts about this. If you watch the full videos and not a mash up, you’ll see most drivers drive long routes without any problems with the software. It’s the edge cases you’re s…

> Honest question, do you think a Tesla that doesn’t recognize whats in front of it to 100% should stop in the road? I saw this recently with Waymo and it stayed blocking traffic until a Waymo tech arrived then the car tried to drive away from the tech. This doesn’t seem like the better answer to me, but I don’t have one.

Answer? Yes. A fully stopped car is a better option than a car that plows into a wall, barriers, or pedestrian.

> Why can’t other companies make self driving software/hardware that a normal person can afford? All other options are insanely expensive and out of reach of anyone but millionaires.

Not sure what you're talking about by "other options". Every other large company I know of is either 1) pursuing self-driving for ride-hailing services, or fleet operations or 2) still not shipping.

But Tesla's aren't exactly cheap, and Tesla cars aren't exactly in the affordable range ($20k) of the working man. A Model3 is $50k with FSD. $60-70k with the performance/long distance versions, and Model S/X well over $100k.

Perhaps you are talking about LIDAR costs and using the old $70,000 LIDAR system that Tesla originally put out FUD about. We all know that in mass manufacturing, the cost of LIDAR would fall, and it has, Velodyne has units that cost only $500 now.

A fully enabled array of consumer Velodyne units, plus radars, and cameras, is going to cost pretty much on par with what Tesla is charging.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#382

Post by TheParkShark »

nullc wrote: post #377
TheParkShark wrote: post #366

Earlier quoted context omitted.

Waymo only works in a 50 sq mi area [1] and has it’s own issues [2]. So no, this is not nonsense. [1] https://arstechnica.com/cars/2021/05/why-hasnt-waymo-expande... [2] https://www.bbc.com/news/technology-57144755

And Tesla FSD is available to what... two dozen parties outside of the company? AFAIK both have extremely limited availability. Waymo doesn't require frequent human intervention to prevent life threatening situations.

Life threatening? Have you ever used cruise control? In most vehicles on the roads today it doesn’t even brake for itself. Should we recall all vehicles with cruise controls cause the drivers don’t pay attention? Perhaps not, and if you watched those videos no lives were threatened, despite your claim. Tech is advancing and you seem to be on the other side of this equation out of some safety issue.

Did you know 38,000 people die in America each year from auto accidents and another 4,400,000 are injured yearly [1]. I would like to see a decrease in unnecessary deaths and accidents on the road. Self driving cars are the future one way or another because they will be safer than humans. Tesla FSD is in beta, in the few hands of what Tesla has deemed as safe drivers based on their driving data. There have been no accidents on FSD and no deaths either. Autopilot is not the same as FSD.

[1] https://www.asirt.org/safe-travel/road-safety-facts/

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#383

Post by cakemuncher »

dyingkneepad wrote: post #324
barbazoo wrote: post #132

Earlier quoted context omitted.

I thought you were making a joke but it really seems to be called "Full Self Driving Beta 9.0". It's hillarious, do they think by adding the "Beta" it makes it ok to hit stuff unless the driver intervenes instantaneously?. How are they even allowed to call it "FSD" ( Full self driving) if in fact it doesn't do that at all?

Well, everything is Beta these days! Is gmail still beta? I wouldn't be surprised to find out Playstation 5 is still marked as Beta.

Gmail has been out of beta since 2009.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#384

Post by plasma »

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…

In one of the technical videos a Tesla engineer presented, I remember the (paraphrasing) quote that the car has no memory and sees the same intersection for the first time, every time. It sounds intentional, as part of their strategy to not rely upon maps etc.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#385

Post by BugsJustFindMe »

fnoof wrote: post #298
BugsJustFindMe wrote: post #278

Earlier quoted context omitted.

> As I've been saying for years now, the first job is to determine that the road ahead is flat enough to drive on. Then decide where you want to drive. I did the DARPA Grand Challenge 16 years ago, which was off-road, so that was the first problem to solve. Tesla has lane-following and smart cruise control, like other automakers, to which they've added some hacks to create the illusion of self-driving. But they just…

The flickering is concerning. Kind of suggests their NN hasn’t learned basic object persistence yet.

That's the thing. The software shouldn't have to "learn" fundamental basic real world shit like that. We KNOW that things don't just flicker in and out of existence. The system should be built on that premise from the start.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#386

Post by studentrob »

valine wrote: post #372
rhinoceraptor wrote: post #347

Earlier quoted context omitted.

It’s a public beta, as far as I can tell it’s available to anyone with a Tesla with the FSD package.

This is simply untrue.

Let's clarify. It's public in the sense that a limited number of customers are driving with this on public roads.

Also, Elon keeps promising "the button" which would allow any Tesla FSD "owner" to get the software.

A number of people shelled out $10k for this software that they do not yet have. So there is a real possibility that it may soon be made available to everyone.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#387

Post by mritun »

CreepGin wrote: post #126
mritun wrote: post #123

Question: Would it be awesome if FDA allowed Pharma to conduct drug-tests like this? Put a "beta-2.9" on the vial and let people try it out... Some may die, be disabled or may linger in vegetative state life-long, but it was their choice afterall and the it can argued that medicinal side-effects are very small cause of mortality and hence long-term the "public beta tests" will make drugs more effective and save more…

Depends on how much the drug costs. If it costs 100k a pop, then I don't see the general public being affected by it too much. RIP those brave rich souls.

General public is affected. A Tesla can cause accident on a public road with other drivers on the road, or cause a cascade or a pile-on - innocent bystanders can die or be injured.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#388

Post by MobileVet »

For a company that exists because of technological and economy of scale gains, primarily in battery tech, it was always odd to me the way Elon would say LIDAR was too expensive or not fast enough. LIDAR et al have come a long way in the last 5 years and will continue to evolve at an exponential rate due to the efforts being put into them.

Yes, I get it, humans use 2 eyes only, but sensor fusion of complementary technologies is so powerful. When lives are on the line, having more than one type of sensor involved is just prudent engineering.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#389

Post by studentrob »

ricardobeat wrote: post #360
tartrate wrote: post #195

Earlier quoted context omitted.

Not sure if 99.99% refers to distance or time, but either way I'm not sure it's a good metric since it only takes a second or two to kill someone.

The same applies to easily distracted human drivers. 1.3 million people die in car accidents every year.

Apples to apples would be comparing miles driven on FSD autopilot to miles driven by human drivers in similar makes of vehicle on the same types of roads in the same weather conditions.

Human drivers don't steer towards concrete pillars every time they drive down the street.

Re: Scenarios in which Tesla FSD Beta 9.0 fails

#390

Post by mritun »

edude03 wrote: post #337
mritun wrote: post #123

Question: Would it be awesome if FDA allowed Pharma to conduct drug-tests like this? Put a "beta-2.9" on the vial and let people try it out... Some may die, be disabled or may linger in vegetative state life-long, but it was their choice afterall and the it can argued that medicinal side-effects are very small cause of mortality and hence long-term the "public beta tests" will make drugs more effective and save more…

I'm pretty sure this is a logical fallacy. In the case of medications it's actually a fairly common situation where a patient has a terminal illness that there is no treatment available for, but you can get it on "the blackmarket" and in that case, it's either die for sure, or maybe not die, and in that case having a beta makes sense - it ensures you're atleast getting the thing you think you're getting. To me autono…

Better than the `alternative` ?... which is drive the car like everyone else?

Why do Tesla drivers get the privilege to beta-test their cars on public road with everyone else around and potentially in their kill-zone?

Post reply on HN