[vel0city]

I don't trust anything Tesla posts on their website about self driving. They've been known to post entirely fictional stories about their self driving. Crazy you still choose to believe them after they've been known to so brazenly lie there.

[ggreer]

David Moss is a traveling LiDAR salesman. He doesn’t work for Tesla, and Tesla didn’t know about him until one of his tweets about his FSD experience went viral. Unless you think he faked images of his FSD stats for months and Tesla went along with it, I’m not sure what to tell you.[1]

1. https://x.com/DavidMoss/status/2010608939751047484

[vel0city]

I don't know who David Moss is, I have no reason to trust him. His tweets I can see are practically nothing but Tesla and Grok shill posts.

[ggreer]

Let’s say, hypothetically, that someone has gone thousands of miles on FSD without intervening. What information would need to exist to convince you of this?

[ImPostingOnHN]

The verified, raw data of at least 1,000 other people's worth of data, so the data has a chance of being statistically significant, rather than 1 random dude out of billions posting on the car company CEO's website (on which said CEO is infamous for moderating content to suit his views and ego).

[ggreer]

That’s what it will take for you to believe that someone has gone thousands of miles without intervening? I don’t think that even Waymo (which has thousands of vehicles that have gone much farther without human intervention) has met the criteria you’ve set.

[UltraSane]

If one person can do this then thousands should also be able to.

[ImPostingOnHN]

Happily, I don't care about Waymo. I do care about statistical competency among the population. Everyone should know that a single data point is irrelevant, as it could be noise just as easily as it could be signal. It is statistically insignificant.

You can actually do the math to find out the sample size you would need to derive a statistically significant conclusion. No need to be incredulous at my answer to your question: it's basic statistics.

As an aside: in general, if you find yourself going to a single person for data and expertise, you might be falling victim to a personality cult.

[vel0city]

More than a random Twitter feed and a news post from a company which is known to spread lies, that's for sure.

[ggreer]

How about if a guy who wrote an article titled Five Things My Roomba Does Better Than My Tesla[1] later drove across the country without intervening?[2] Unless all three people in the car are lying, it seems like an independent example of going thousands of miles without intervening.

1. https://www.thedrive.com/opinion/40604/five-things-my-roomba...

2. https://www.thedrive.com/news/a-tesla-actually-drove-itself-...

[vel0city]

> Both are deeply knowledgeable about Tesla’s Full-Self Driving suite and Roy stressed that he couldn’t have completed the trip without them.

Totally fully self driving even though you need not one, not two, but three autonomous driving experts with you. And be sure to have a second car with you when your first autonomous vehicle strands you. Sure sounds like a reliable system ready for the masses to use on public roadways!

[tmule]

That’s a terribly low bar for evidence - it’s deciding to pick whatever self-reported data confirms your priors. Far more than 3 individuals believed that Ivermectin cured them of COVID - I, however, chose to not believe them and get vaccinated instead. FWIW, my experience with FSD on HW4 is that I don’t need to intervene roughly for a 100ish miles on a clear day on a freeway without construction or accidents. That’s good enough for me to subscribe during roadtrips, but Musk and his legion of supporters is overselling capabilities - as usual.

[UltraSane]

cryptographically signed timestamped raw log data.

[electriclove]

Ok, try it yourself with a new HW4 and you will see.

[vel0city]

I've ridden in Teslas many times operating in "FSD" (read: not fully, and not self, driving), nearly every time its made some kind of moving violation including nearly hitting a pedestrian. No thanks.

I heard the same thing in 2019, HW3 solved all the issues, it finally just works as advertised. That was after HW2 was guaranteed to ship with all the hardware needed for FSD a decade ago, for real this time.

I'll probably wait for HW5, then you'll tell me its really there. This time it won't even run people over, and it actually stops at stop signs more than just 98% of the time.

Personally I try and avoid systems that drive people in front of trains. https://www.youtube.com/watch?v=vMqTmOTtft4