>
would AI driving not fail there too?It might if it were relying solely on a GPS and nothing else, but, of course, none of them do that. The biggest difference is that navigation software can improve and sensors don't stop paying attention. You can't say either of those things about people who screw up in exactly the same circumstances.
> Heres an example of AI driving into a river https://electrek.co/2019/03/10/tesla-crash-river-claim-unint.... so it happens as well.
Let's note that the article is skeptical that the problem was actually the car:
"I want to give the driver the benefit of the doubt, but every time we have seen similar circumstances, the logs always pointed to a user mistake."
But even giving the driver the benefit of the doubt and asserting as a premise that the AI caused the accident, we're still left with the fact that people unintentionally accelerate their vehicles all the damn time. If a machine does it once in a while, that's not a regression, that's the baseline.