News for hackers. Stuff that matters.
Re:Tesla is close to becoming the most valuable car company by jcranmer on Thursday June 11, 2020 @10:48AM (#23489495)
It's been such a long time since I've heard someone trot out the "Tesla has the best raw data" canard that I thought it had finally died off for real.

For starters, Tesla still seems to have this annoying habit of not detecting large, white trucks that are stopped in the middle of the highway, and will happily drive into them at full speed. This isn't exactly an "edge case" issue here.

Re:Tesla is close to becoming the most valuable car company by sixQuarks on Thursday June 11, 2020 @12:04PM (#23490259)
I didn't say best raw data. Lidar obviously produces better raw data on an individual basis. Tesla has more real-world driving data overall. Nevertheless, it doesn't matter. Tesla is the only one going all-in on vision based self driving. That's the key thing that's going to get us to full self driving. Everyone will eventually need to do this.
Re:Tesla is close to becoming the most valuable car company by jcranmer on Thursday June 11, 2020 @12:51PM (#23490758)
> I didn't say best raw data. Lidar obviously produces better raw data on an individual basis. Tesla has more real-world driving data overall.

The "real-world driving data" is what I'm calling the "raw data" here, as it's the raw data from the standpoint of the (perceived) AI algorithms driving self-driving cars.

> Tesla is the only one going all-in on vision based self driving. That's the key thing that's going to get us to full self driving.

Why is it the key thing? Why should worsening the quality of your input data improve the results?

Re:Tesla is close to becoming the most valuable car company by sixQuarks on Thursday June 11, 2020 @03:08PM (#23492278)
Because the important part is the software that interprets that data.

Our eyes get worse data than lidar, yet our brains are able to process this data more effectively.

Also, lidar is super expensive. It will take much longer to get affordable lidar into everyday vehicles.

Re:Tesla is close to becoming the most valuable car company by jcranmer on Thursday June 11, 2020 @04:05PM (#23492827)
The hardware necessary to emulate our brain capabilities with neural nets is several orders of magnitude more expensive than lidar.

Running with a more responsible hardware stack means the software has to be more cleverly designed, and that design is mostly not in the just-throw-data-at-a-neural-net stage. Building your visible-light-only driving system is going to cause you to struggle a lot harder at getting a good subroutine for "how far away is that object?" while providing you no benefit to solving the harder problem of "what will that object react to my coming nearer to it?"

Re:Tesla is close to becoming the most valuable car company by sixQuarks on Thursday June 11, 2020 @06:06PM (#23493783)
I was using an analogy with the brain. You don't have to replicate a brain for full self driving.
Re:Tesla is close to becoming the most valuable car company by OldHand2018 on Thursday June 11, 2020 @11:07AM (#23489665)
> For starters, Tesla still seems to have this annoying habit of not detecting large, white trucks that are stopped in the middle of the highway, and will happily drive into them at full speed. This isn't exactly an "edge case" issue here.

<joke>To be fair, it was an edge case until Tesla started selling cars.</joke>