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

Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

electrek.co

Post reply on HN
Print view View original

331–340 of 410 posts

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#331

Post by senordevnyc »

ACCount37 wrote: post #303
senordevnyc wrote: post #299

Earlier quoted context omitted.

We don't have a bottleneck anymore. We have Waymo. They seemed to have solved whatever the issue was...I wonder what the main difference between the Waymo system and the Tesla system is?

The "main difference" is that Waymo wouldn't even try to drive coast to coast. Because it's geofenced to shit. Restricted entirely to a few select, fully pre-mapped areas. They only recently started trying to add more freeways to the fence.

You're right, they wouldn't try, but I don't think there's any evidence for the idea that Waymo couldn't pull this trip off now from a technical POV. Even if they're pre-mapping, the vehicles still have to react to what's actually around them.

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#332

Post by tzs »

testing22321 wrote: post #106
petesergeant wrote: post #3

> Tesla’s EV business is in decline and the stock price depends entirely on the self-driving and robot promises I don't think that's right; I think the stock price entirely depends on people seeing it a vehicle to invest in Musk. If Musk died tomorrow, but nothing else changed at Tesla, the stock price would crater.

The world’s best selling vehicle means nothing? Extremely safe vehicles mean nothing? I get that it’s way over hyped, but they have real results that can’t be denied

The best selling model counts for something, but even with that Tesla just isn't a big car company when compared to the other major car companies.

They have the best selling vehicle by a little under 1%, with the Tesla Model Y just edging out the Toyota Corolla. But Toyota also has the 3rd best selling model (RAV4) that is about 7% behind the Model Y. And they have a third model in the top 10, the Camry, at a little over half the Model Y sales.

Just those 3 Toyota models combined sell about 30% more than all Tesla models combined.

Across all models Toyota sells 6 times as many cars as Tesla.

By number of cars sold per year Tesla is the 15th biggest car maker. The list is Toyota, Volkswagen, Hyundai-Kia, GM, Stellantis, Ford, BYD, Honda, Nissan, Suzuki, BMW, Mercedes-Benz, Renault, Geely, and then Tesla.

If we go by revenue from sales rather than units sold it is 12th. The list is: Toyota, Volkswagen, Hyundai-Kia, Stallantis, GM, Ford, Mercedes-Benz, BMW, Honda, BYD, SAIC Motor, and then Tesla.

Yet Tesla has something like 6 times the market cap of Toyota and around 30 times the market caps of VW and Honda. That's pretty much all hype.

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#333

Post by ncruces »

rkomorn wrote: post #91
jeffbee wrote: post #85

Earlier quoted context omitted.

You might have also noticed that the pavement is terrible. Mostly this comes down to the fact that in Europe the fuel taxes 3-4x ours.

Not just that but also tolls. There are way more toll roads, at least where I've lived in Europe, compared to where I've lived in the US (Spain being the one very noticeable exception between France and Portugal).

Yeah, in Portugal the highway operator would be liable for that accident.

They'd be liable if even if it was road kill, as they're responsible for ensuring big animals don't go into roads.

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#334

Post by pavlov »

whatevaa wrote: post #324
pavlov wrote: post #160

Earlier quoted context omitted.

He lies relentlessly even to customers who paid for the product. I know because I’m one of them. FSD paid in full almost seven years ago, still does absolutely nothing in Europe. A five-year-old would do a better job at driving because the Tesla can’t even see speed limit signs correctly. Tesla takes no responsibility for their misleading marketing and years of lies. Most recently Musk promised in early 2025 that the…

Why did you buy FSD if you are in Europe?

Why did Tesla sell a 7,500 euro feature in Europe if they knew it’s never going to work?

My mistake was assuming this company had the slightest decency to sell things they could actually deliver.

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#335

Post by pavlov »

enslavedrobot wrote: post #328
samrus wrote: post #202

Earlier quoted context omitted.

So why take money for it? And computer vision is well past the stage where the information can be read from these signs, theres enough training data. So thats not a real hurdle. If different road geometry or traffic customs/rules is the issue then just admit that FSD cant generalize like a human and is overfit to the us. Why lie and pretend its almost human level?

It is purely a regulatory problem. FSD is not available in Europe due to the slow pace of regulatory approval. For instance UNECE regulation 79 prevents FSD from using its full capacity to turn the steering wheel. It's a rat's nest of red tape.

How do EU regulations prevent my car from recognizing speed limit signs?

The real problem is that Tesla sold this in Europe, but never put the slightest effort towards actually developing the localized ML model that could make it work. (Of course the hardware sucks too, but they could have done a much better job with it.)

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#336

Post by cameldrv »

foobarian wrote: post #159
tptacek wrote: post #125

Earlier quoted context omitted.

Humans routinely drive from LA to NYC without wrecking their cars. In fact, that's the normal outcome.

I've been driving on local and highway roads for 30 years now and I have never come across a piece of debris so large that driving over it would damage my car. Seeing that video, I don't have high confidence that I would have dodged that hazard - maybe 70% sure? The thing is, usually there is plenty of traffic ahead that acts very obviously different in situations like this that helps as well. All that to say that I…

No way. I call in road debris on the freeway once every couple of months. People swerve around it and if it’s congested, people swerving around it create a significant hazard.

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#338

Post by testing22321 »

tzs wrote: post #332
testing22321 wrote: post #106

Earlier quoted context omitted.

The world’s best selling vehicle means nothing? Extremely safe vehicles mean nothing? I get that it’s way over hyped, but they have real results that can’t be denied

The best selling model counts for something, but even with that Tesla just isn't a big car company when compared to the other major car companies. They have the best selling vehicle by a little under 1%, with the Tesla Model Y just edging out the Toyota Corolla. But Toyota also has the 3rd best selling model (RAV4) that is about 7% behind the Model Y. And they have a third model in the top 10, the Camry, at a little…

So a thing has to be among the “world’s biggest” to be of note?

Of course not.

They don’t make as many vehicles or have the revenue of other auto manufacturers, but who cares.

What they do, they do very, very well. They lead to mass market EV adoption. Even if they crumble tomorrow their contribution is immense. Who cares about market cap, it’s all just gambling.

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#339

Post by anonymars »

whatevaa wrote: post #324
pavlov wrote: post #160

Earlier quoted context omitted.

He lies relentlessly even to customers who paid for the product. I know because I’m one of them. FSD paid in full almost seven years ago, still does absolutely nothing in Europe. A five-year-old would do a better job at driving because the Tesla can’t even see speed limit signs correctly. Tesla takes no responsibility for their misleading marketing and years of lies. Most recently Musk promised in early 2025 that the…

Why did you buy FSD if you are in Europe?

I will never understand why people ask why those who bought a thing expected to get that thing

Isn't that the bare minimum requirement for how commerce is supposed to function?

Re: Tesla influencers tried coast-to-coast self-driving, hit debris before 60 miles

#340

Post by cameldrv »

ACCount37 wrote: post #77
coreyh14444 wrote: post #7

Earlier quoted context omitted.

The debris is pretty close to the color of the road. Seems like a good case for radar/lidar ¯\_(ツ)_/¯

Yeah! Just add more sensors! We're only 992 more sensors away from full self-driving! It totally works that way! The debris? The very visible piece of debris? The piece of debris that a third party camera inside the car did in fact see? Adding 2 radars and 5 LIDARs would totally solve that! For fuck's sake, I am tired of this worn out argument. The bottleneck of self-driving isn't sensors. It was never sensors. The b…

It’s a lot easier to make an AI that highly reliably identifies dangerous road debris if it can see the appearance and the 3D shape of it. There’s a fair bit of debris out there that just looks really weird because it’s the mangled and broken version of something else. There are a lot of ways to mangle and break things, so the training data is sparser than you’d ideally like.
Post reply on HN