News for hackers. Stuff that matters.

A comment on Normalized crash data shows Autopilot is much less safe than Tesla claims. Parent comment

Re:Normalized crash data shows Autopilot is much less safe t... by ClumsyPilot on Wednesday February 02, 2022 @11:27PM (#30188677)
"Example: Traffic Resolution advisories require a 5 second reaction time"

When the Autopilot swerves into a concrete wall for no reason, you will have 0.5 seconds left to live. Rwacting in the last 0.1 secons bwf9re collision will not save you - you must react in like 200ms.

It is physically impossible to react in time to some autopilot mistakes, stop defending this idiocy.

https://futurism.com/the-byte/tesla-drivers-autopilot-swerve...

[ Parent | on HN ]
Re:Normalized crash data shows Autopilot is much less safe t... by Dylan16807 on Thursday February 03, 2022 @12:46AM (#30189131)
The problem is bad enough that it killed someone; you don't need to use exaggerated made-up numbers.

In the example video the car starts turning at 40 seconds and passes the barrier at 47 seconds.

[ Parent | on HN ]
Re:Normalized crash data shows Autopilot is much less safe t... by ClumsyPilot on Thursday February 03, 2022 @09:26AM (#30192772)
Surely you can see how you might have less than a second to react if Autopilot swerves into the oncoming traffik? I can't search all tesla accidents by 'least time to react'
[ Parent | on HN ]
Re:Normalized crash data shows Autopilot is much less safe t... by Dylan16807 on Thursday February 03, 2022 @01:18PM (#30196331)
If they actually do that, it could be a problem, but I'm not convinced that's a failure case that we need to worry much about.
[ Parent | on HN ]