In the piece — titled “Can You Fool a Self Driving Car?” — Rober found that a Tesla car on Autopilot was fooled by a Wile E. Coyote-style wall painted to look like the road ahead of it, with the electric vehicle plowing right through it instead of stopping.
The footage was damning enough, with slow-motion clips showing the car not only crashing through the styrofoam wall but also a mannequin of a child. The Tesla was also fooled by simulated rain and fog.
Were is a robust description of the experiment? Or am I supposed to look frame by frame at the screen in the car to deduce the testing conditions?
All he had to do was tell us clearly what is enabled on each car and what his inputs are. That would solve all the tesla fanbois comments about him cheating. Maybe he didn’t for „engagement”.
deleted by creator
He made an elaborate test track specifically to make interesting observations.
He set up dozens of cameras to record interesting observations from multiple angles.
He collected footage of interesting phenomena he observed as they were happening in his elaborate test environment.
He then cut the footage up so much it’s impossible for us to say exactly what really happened.
If he went to all this trouble, and then made claims based on his experiment would it really hurt the video to explain the testing process a little bit more?