I don't like those headlights also. I think it's a case of when founders bring too much of their personality into the product. Otherwise great product and this self drive system at least has a sound start (track objects across video frames)

Why look foolish if you don't have to?

"You are right, that was a red light!"

At first I was skeptical, but reading the article, they do track object across video frames which for me it's the minimum a system like this should do. All previous FSD systems are just Fake self-driving.

"That proprietary AI driver identifies features in images and point clouds, groups them into objects, and tracks them across frames, time-stamped to the millisecond to account for differing frame rates. The AI thus builds confidence over time, acting on object detections that persist across several frames, rather than, say, slamming the brakes due to a camera blip on a single frame."

>they do track object across video frames which for me it's the minimum a system like this should do. All previous FSD systems are just Fake self-driving.

I'm pretty sure Waymo does this. It's hard to imagine not using this information, it's basically 50% of what I do when driving (e.g. that kid that was running on the sidewalk suddenly disappeared from view in an unexpected way; I wonder if he's about to cut across the street, etc).

I wander what it does for different objects.

Oups a ball crossed the street 15m ahead. Let's slowdown to a crawl and watch for the kid is what a human would do.

I suppose they may have special cased the ball case.

This is very basic for any self driving car system you can see on the road today or even 10 years ago.

> The AI thus builds confidence over time, acting on object detections that persist across several frames, rather than, say, slamming the brakes due to a camera blip on a single frame.

Nice in theory but in practice they still need a ton of training data. The bitter lesson is very bitter. Tesla's end to end FSD uses occupancy networks and brake stabbing still hasn't been fully solved.

> slamming the brakes due to a camera blip on a single frame

Ironically, I'm sure most humans have done the eyeball equivalent a handful of times, despite our knowledge of object permeance.

Where did he said that? A new experiment can be done, responsibly, right?

The difficulty in getting to an agreement on what "responsible" means, and on how a "failure" should be handled means that said experiment will never occur. Nothing is ever safe enough and no failure is acceptable -- so no test which can fail can be run.

A situation which would be in obvious conflict (negative expected value) with the goal of saving the man hours and lives currently being cost by manual driving.

Add facebook too. No problem for them to accept money from websites that were reported as fraud. They pause it a little then they are right back at it.

This is not a game. Choosing from wrong answers only is not a game.

First you introduce the tax, then you increase it. Minimum public anger. They messed up because it's a recycling tax that I presume does not apply to... everything? So it feels punitive. Also it's big. I pay way less recycling tax on bigger and harder to recycle items.

when I switched from Windows to Apple the amount of ads was the same. The only thing that changed was that they were Apple's ads. Apple hardware is great, but it's being severely botched by it's software. Seems like software is hard, no matter how much money you have.

good thing is not climate change, that would be really bad...

Sometimes is hard to understand what really happens for me. So regular people compete on price with companies? That is wild. Here the industry in general is the first one to get disconnected from power if there is not enough. This also creates an incentive for people with money to solve the power generation problem that they themselves created.

Agriculture pays, on average, probably something like 1/1000th of what residential users pay for water.

Does much agriculture use the sanitized municipal water supply?