Live data from Hacker News

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

electrek.co

71–80 of 410 posts

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

#71
post #12

Earlier quoted context omitted.

Solar roofs, Dojo, Hyperloop, robotaxi, roadster, semi, mission around the Moon, man on Mars by 2020, it’s all coming guys he promised!

[flagged]

the problem is that TSLA (the company) is pivoting hard to humanoid robots, which is a relatively easier problem, perfectly big market and Musk is a terrific salesguy. Medium/long term, humanoid robots are commodity but so were electric cars and TSLA (the stock) rode that to glory.

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

#74
post #53

I got my first Tesla last year and my first trip with FSD was just after the launch of V13, so I could not compare it to earlier versions. But I was shocked by how good it was. I completed a 800 miles trip with a handful of interventions, most or all of them likely unnecessary. Even with rain the system worked well. I don’t understand how the system was not able to see this obstacle and slow down or change lanes. Did…

Even with traffic tailgating it would need to brake or go to then right. Your comment sounds like a Tesla ad written by someone from Tesla or a heavy, heavy fan boy.

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

#75
post #43

Earlier quoted context omitted.

Well, I have to admit that your friend has a point. Humans are bad at reacting quickly and correctly to unexpected situations, and some debris large enough to damage your car showing up from out of nowhere after several hours of boring driving along a largely straight highway with little traffic is definitely one of these situations. But a self-driving system worth its salt should always be alert, scanning the road a…

The humans in the vehicle spotted it fine, and we should not tolerate self-driving systems that are only as good as the worst of us.

> and we should not tolerate self-driving systems that are as good as the worst of us

The person you replied to didn't do that, though:

> But a self-driving system worth its salt should always be alert, scanning the road ahead, able to identify dangerous debris, and react accordingly. So, different pair of shoes...

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

#76
post #57

What is the point of "testing" something that everyone knows doesn't work and only exists because a serial liar said so? If Musk says you will survive a fall from a 90-stories high-rise... don't test it.

We should rigorously test the things we’re most skeptical of.

You shouldn’t take pills a stranger gives you at a music festival without checking them for loads of things, for example. Even if you don’t ever intend on consuming them it’s nice to have specific accusations with evidence.

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

#77

It's so clear, dry, perfect lighting, no traffic or anything. That's shocking.

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 bottleneck of self-drivng always was, and still is: AI.

Every time a self-driving car crashes due to a self-driving fault, you pull the blackbox, and what do you see? The sensors received all the data they needed to make the right call. The system had enough time to make the right call. The system did not make the right call. The issue is always AI.

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

#78

A lot of apologists say that "a human would have hit that". That's kind of irrelevant, this technology is meant to be safer and held to a higher standard. Comparing to a human is not a valid excuse...

A human would not have hit that, the two guys see it coming from a long time and would have stopped or changed lanes like.

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

#79

Tangentially - If you as a European happen to drive on US highways, you will noticed that they are heavily littered with fallen cargo, aluminum ladders, huge amount of shredded tires and occasionally a trailer without a towing car... It has been so bizarre for me to observe this. Nobody is cleaning that?

Why are Dutch or Swiss highways so much more pristine than French and German ones?

Have you compared distances?

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

#80
post #53

I got my first Tesla last year and my first trip with FSD was just after the launch of V13, so I could not compare it to earlier versions. But I was shocked by how good it was. I completed a 800 miles trip with a handful of interventions, most or all of them likely unnecessary. Even with rain the system worked well. I don’t understand how the system was not able to see this obstacle and slow down or change lanes. Did…

When they first released V13, the highway stack was still the old C++ code. It wasn't until another four or five months that they switched it to a neural network. It doesn't seem like they've put much focus on it since then.
Post reply on HN