> These challenges are all about edge-cases, and responding safely to changing conditions and misbehaviors from other agents... The response cannot be "let's add a ton of fragile electronics"
Self driving car has failed to detect a person in the dark and killed her. It was demonstrated that Tesla autopilot fails to detect a child crossing the road. It confused a semi trailer and an underpass. You call that an edge case?
> The response cannot be "let's add a ton of fragile electronics in all of the infrastructure"
So instead we will add a ton of fragile electronics in every car. Instead of having 3 optimally positioned lidars monitoring an intersection, we will have 20 poorly positioned lidars on every car.
You don't need electronis, you can use paint. You can put QR codes that tell a car where it is in an underground parking lot. If we add a parrern to all clothing in infrared-only paint, that would help various AI detect people and tell them apart from surroundings. You can put a metal patterns on street signs that are detected by automotive radar.
> will cost a ton of money to build and maintain
And electronics in the cars will cost even more
> will break in weird ways over time and lead to cascading failures
You mean like the failure the main article is discussing right now?
> it's dubious that it would even work at all
And it's dubious this 'individual' approach will ever work. Every single argument you've made equally applies to the approach you are advocating.
Self driving car has failed to detect a person in the dark and killed her. It was demonstrated that Tesla autopilot fails to detect a child crossing the road. It confused a semi trailer and an underpass. You call that an edge case?
> The response cannot be "let's add a ton of fragile electronics in all of the infrastructure"
So instead we will add a ton of fragile electronics in every car. Instead of having 3 optimally positioned lidars monitoring an intersection, we will have 20 poorly positioned lidars on every car.
You don't need electronis, you can use paint. You can put QR codes that tell a car where it is in an underground parking lot. If we add a parrern to all clothing in infrared-only paint, that would help various AI detect people and tell them apart from surroundings. You can put a metal patterns on street signs that are detected by automotive radar.
> will cost a ton of money to build and maintain
And electronics in the cars will cost even more
> will break in weird ways over time and lead to cascading failures
You mean like the failure the main article is discussing right now?
> it's dubious that it would even work at all
And it's dubious this 'individual' approach will ever work. Every single argument you've made equally applies to the approach you are advocating.