Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> doesn’t seem capable of solving it,

How so?

If humans can master driving with 2 eyes looking forward, why would a car with plenty of cameras in all directions not have sufficient sensory input to master it?

The problem is the software, not the sensors.



Same reason airplanes don't fly by just flapping their wings like birds. There's not always a biological equivalent for solving a problem, especially when you take into account human brain's evolution over millions of years. Sometimes computers need more help.


Large birds don't fly by flapping their wings when they have enough lift. Look at one in a thermal updraft sometime, it's quite a majestic sight.

If birds had engines on their wings, they would probably fly more like airplanes.

But cameras are a poor substitute for human vision, because they can't move or pivot or refocus much.


It does seem reasonable, though, that if humans can solve safe driving with a brain mass (3 lbs) that computers wouldn't need that much more help. Put another way: every machine learning "expert" who has a kid is amazed to learn how simple unsupervised learning is and how few training examples are required.


You use far more input when you drive than just your eyes. Suggesting otherwise is just obtuse.


not much similar between eyes (incl the full sensory processing) and camera sensors

you're using elon's own argument btw, are you repeating that knowingly




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: