News for hackers. Stuff that matters.
Re:Driverless robotaxi fleet paralyzed for hours in San Fran... by al_borland on Thursday June 30, 2022 @10:18PM (#31941439)
I'd be curious on the statistics related to new under-developed FSD software vs a new teenage driver.

The only way for either of these things to get better is through real-world experience.

Re:Driverless robotaxi fleet paralyzed for hours in San Fran... by dbcurtis on Friday July 01, 2022 @12:35AM (#31942416)
Actually, autonomous driving stacks can get better doing millions of miles in simulation. The teen, not so much.
Re:Driverless robotaxi fleet paralyzed for hours in San Fran... by lelanthran on Friday July 01, 2022 @01:47AM (#31942815)
> Actually, autonomous driving stacks can get better doing millions of miles in simulation. The teen, not so much.

Have they not already completed many millions of miles in simulation, back in 2018?

To me, it looks like self-diving capabilities have reached a maxima. The resources poured into it have barely been needle movers in objective metrics.

Re:Driverless robotaxi fleet paralyzed for hours in San Fran... by extheat on Friday July 01, 2022 @02:10AM (#31942965)
Disagree. It’s easy to see how far FSD has progressed, there’s lots of videos to document how far it’s gone from then and today. It’s also not easy to say they’ve reached the point of diminishing returns (which generally takes a massive amount of data to hit, even GPT3 has not hit it) as it’s not clear how much of FSD is powered by heuristic based code and what is NNs. Judging by some of the discussions there’s still a significant amount of C/C++ code in the loop that could be improved by moving them to NNs.
Re:Driverless robotaxi fleet paralyzed for hours in San Fran... by lelanthran on Friday July 01, 2022 @03:14AM (#31943374)
> Disagree. It’s easy to see how far FSD has progressed, there’s lots of videos to document how far it’s gone from then and today.

Yeah, but videos aren't objective metrics. For me, an objective metric is "went $FOO miles in $BAR conditions without needing any intervention".

What would you consider an objective metric?

Re:Driverless robotaxi fleet paralyzed for hours in San Fran... by ra7 on Friday July 01, 2022 @05:30AM (#31944165)
Actually, intervention is also not the best metric. The best metric is driverless miles. Removing the driver is the true test of autonomy.
Re:Driverless robotaxi fleet paralyzed for hours in San Fran... by popinman322 on Friday July 01, 2022 @05:36AM (#31944200)
> "went $FOO miles in $BAR conditions without needing any intervention"

But who decides whether intervention was necessary? This is still too vague.

Re:Driverless robotaxi fleet paralyzed for hours in San Fran... by lelanthran on Friday July 01, 2022 @06:02AM (#31944372)
> But who decides whether intervention was necessary? This is still too vague.

Irrelevant - until the car has actually gone without an intervention for whatever the median is for human drivers[1], we can't very well claim that it is safe for use.

[1] The average human driver goes hundreds of thousands of kilometers without crashing.

Re:Driverless robotaxi fleet paralyzed for hours in San Fran... by seoaeu on Friday July 01, 2022 @12:48AM (#31942502)
Target practice on pedestrians and stationary objects? Just because self driving software can get better from simulation doesn’t mean it will
Re:Driverless robotaxi fleet paralyzed for hours in San Fran... by jvanderbot on Thursday June 30, 2022 @11:24PM (#31941955)
I wouldn't get in the car with a new teenage driver, nor will I enable self-driving on my cars for a long, long time.

And I work in robotics.

Re:Driverless robotaxi fleet paralyzed for hours in San Fran... by enriquto on Friday July 01, 2022 @12:27AM (#31942360)
Yet every day you get in the road with new teenager drivers (and drunk people, and idiots of all sorts). Doesn't that scare you?

Driving is terrifying.

Re:Driverless robotaxi fleet paralyzed for hours in San Fran... by al_borland on Friday July 01, 2022 @01:32AM (#31942730)
Every time I hear people say they don't trust anyone, I wonder if they drive, as it requires an insane level of trust in the rest of humanity.
Re:Driverless robotaxi fleet paralyzed for hours in San Fran... by jvanderbot on Friday July 01, 2022 @01:17PM (#31949614)
I am the person I trust the most in my immediate vicinity. Removing me sounds like a downgrade in trust in the overall experience. To my selfish self.
Re:Driverless robotaxi fleet paralyzed for hours in San Fran... by jvanderbot on Friday July 01, 2022 @01:13PM (#31949544)
Yes, it does. Luckily, I can drive defensively against other actors since my vehicle is essentially a bunch of armor, safety gear, and also an escape means.

But how does one defend themselves when the vehicle does not want to do so due to inexperience or negligence? Best you can do is hope it doesn't decide for you that your infant's carseat is the best place to collide with a semi it just noticed because it was gray in fog, and oh by the way the CEO decided not to use lidar or radar, and oh this particular ice patch was not in the training set. If you don't trust lvl 5 in those conditions, you don't really trust lvl 5.

Re:Driverless robotaxi fleet paralyzed for hours in San Fran... by ClumsyPilot on Friday July 01, 2022 @07:34AM (#31944938)
> The only way for either of these things to get better is through real-world experience

if you are going to make that argument, you have to explain why we are socialising losses and privatising profits (again)

so some number of people will be injured of killed while self driving cars gain experience, and then private corporations will extract profit from it?