Hacker News new | past | comments | ask | show | jobs | submit login

>This is why self-driving cars still elude us, but will be so much safer than human drivers when they finally do arrive.

Isn't that just a by definition thing?

My Tesla can already drive itself, I don't trust it and I don't think it's safe. When I get one that I trust and is safe then it will be safer than me, and by extension other humans.

The problem is that the current generation of algorithms are brittle.




The "just put a brick on the gas pedal" algorithm was particularly prone to crashing.


Yes, but it had the lowest CPU and memory footprint! There's also something to be said about the COTS hardware requirements and ease of installation.




Join us for AI Startup School this June 16-17 in San Francisco!

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

Search: