News for hackers. Stuff that matters.

A comment on Uber Neglected Simulation Testing on Self-Driving Cars, Insiders Say. Parent comment

Re:Uber Neglected Simulation Testing on Self-Driving Cars, I... by wpietri on Tuesday June 19, 2018 @05:59PM (#17350623)
I'd be interested to see your stats comparing the two crash rates. Note that you have to compare equal conditions; most self-driving tests are done in unrealistically good ones. (Which is fine for pilot programs, but makes the stats hard to compare.)

But you're already no-true-scotsmanning your way to giving the self-driving cars unrealistically good scores. Yes, a cause behind the Uber crash is indeed Uber disabling a safety system they thought unnecessary. But we have no reason to believe some other companies aren't also either turning off or just never adding safety systems.

[ Parent | on HN ]
Re:Uber Neglected Simulation Testing on Self-Driving Cars, I... by beat on Tuesday June 19, 2018 @06:15PM (#17350718)
On the other hand, if we're worried about the performance of these systems, shouldn't we be testing them in ideal conditions before submitting them to suboptimal conditions?
[ Parent | on HN ]
Re:Uber Neglected Simulation Testing on Self-Driving Cars, I... by wpietri on Wednesday June 20, 2018 @10:16AM (#17355564)
Yes, which is why I explicitly said it was fine for pilot programs.

My objection is not to better testing. It's to bad comparisons. Including, as here, with somebody handwaving at data that, at best, couldn't answer the question.

[ Parent | on HN ]