Hacker News new | ask | show | jobs
by a_c_s 753 days ago
Tesla is still years behind Waymo: "FSD 12.3 seems superior to Waymo’s technology circa 2018, it’s not as good as Waymo’s technology at the end of 2020"

https://arstechnica.com/cars/2024/05/on-self-driving-waymo-i...

2 comments

The author's opinion is based on one intervention from one trip:

> "The version of FSD I tried in March [of 2024] was clearly not ready for driverless operation. For example, I had to intervene to prevent the Model X from running over a plastic lane divider, a mistake Waymo would not have made in 2020. So while FSD 12.3 seems superior to Waymo’s technology circa 2018, it’s not as good as Waymo’s technology at the end of 2020."

While true, if you go to page 1 of the article you find this:

> During a 45-minute test drive in a Tesla Model X, I had to intervene twice to correct mistakes by the FSD software. In contrast, I rode in driverless Waymo vehicles for more than two hours and didn’t notice a single mistake.

That seems pretty significant.

While Waymo is only trying to enable itself on 1-2 particular highways in western America, Tesla's FSD can work hours with no interventions on the highways, do exits, and automate pretty much the entire trip on a highway in any place in the US, Canada, and China.

Again, it's just different approaches to solve the problem.

For the record Waymo taxis are not limited to highways in Phoenix, not sure about how they operate elsewhere.
A 45’ drive is not sufficient data for a serious review.
It is if it disengages or requires intervention twice. The major players are at tens of thousands of miles between disengagement. We’re talking days or weeks of non-stop driving without disengagements.
Disengagement on a Tesla (manual override of the specific driver, riding on an unknown route) vs Waymo (pre-mapped tiny geographical area, no info on what counts as disengagement) can not be comparable.
They are both pursuing the same goal: making a self-driving car. That makes them comparable. There's nothing stopping Tesla from pre-mapping; their decision not to do that doesn't suddenly make them incomparable.

The only differentiating factor is that Tesla's approach has theoretical benefits, if they can prove it works. If they could hit the same disengagements/mile rate as Waymo, they would likely be ahead since they don't need pre-mapping.

That being said, theoretical benefits are worth about the same as monopoly money. Until they can demonstrate that they can get the same performance without pre-mapping and LIDAR, it's all just conjecture. There are no points awarded for "yeah, well if mine had worked it would have been better!" They might get there eventually, but the current signs don't seem promising. At least not for getting there before Waymo completely eats the market.

Also, at least Waymo's disengagements are known. They're defined by the DMV, it's basically "any time control needs to be taken away from the autopilot". If a human in the car manually takes over, that's a disengagement. If the car decides it can't drive safely and prompts a human to take over, that's a disengagement. If someone has to log in to the car with a joystick to get it somewhere, that's a disengagement.

The only confusing situation I'm aware of is when remote techs give the car waypoints, like if it gets confused in a parking lot. I don't believe that counts as a disengagement because the car is still driving itself, it's basically just failing at pathfinding. That seems reasonable to me, because it's not a safety risk at all, just an annoyance to the business.

I'm using FSD every day in NYC. It is one of the hardest environments in the world.

99% of interventions I had were from a driver's experience perspective, not the actual safety.

It's still far away from 99.999 that you would expect.

> at the end of 2020

It seems silly to analyze a 4 year old version of something that is changing extremely rapidly.

Both Waymo and FSD have come a very long way since 2020.

You are misunderstanding the quote.

FSD 12.3 is the current version of Tesla's self driving software. The article is comparing that current version of FSD to Waymo's 2020 state and saying that Tesla's self driving code today is worse than Waymo's 4 year ago. That is, according to the quote, Tesla is more than 4 years behind.

Ah, gotcha, thanks. You are right, I misunderstood