Search results

I think it's pretty hard to get at (it's between the door and the side of car.) Someone here with a minivan can probably chime in but I expect you'd need a metal rod to get at it and if the vehicle needs to be metal rod resistant from the inside that's going to be pretty tough!

Ah. I think I've noticed the wiring before. Here's a picture of it. It needs to be about half the slide length.

They've been training FSD on this turn for years. Chuck claims to have met the engineer who created the simulation of it. Not sure how left turns by drivers coming from the right changes things. Those drivers have the right of the way.

It’s a simple unprotected left turn. Whether unprotected left turns are simpler than other types of turns is a much more complicated question. Unprotected left turns are simple because it is very clear who has the right of way and you don't have to worry about mistakes made by other drivers...

Why? They roll down on minivans.

Are we talking about the same turn? I can see fine looking at YouTube video. I've never seen Chuck have to abort for something that wasn't easily visible on the wide angle camera (which is far lower resolution than human eyes).

Not betting on 12.4. No way they're going to get it working by next week.

UPL Team is definitely under the gun!

It was brought up because @HitchHiker71 suggested that the Tesla Robotaxi would initially be L3. Remote operation would allow Tesla to operate many robotaxis per driver. The only other application I can think of is delivering a rental car to someone or paying lower wages to drivers by...

Capabilities and Performance Unlike active safety systems, such as automatic emergency braking(AEB), that intervene only momentarily when necessary to help prevent a collision, active driving assistance systems provide continuous support intended to make driving easier—for instance, when you’re...

Does sound like it. I know someone with some extra American made AVs

Lots of stuff is legal in Nevada.

There are companies that claim it’s possible to safely remotely drive cars. https://vay.io/

Why not use remote assistance so you can have a single “driver” run many robotaxis?

To be pedantic you’re responsible for monitoring that a wheel is about to fall off or the car is on fire.

They probably do the stop sign training with simulated data.

Most of their driving is during the day on Los Angeles interstates (where speed is very often under 40 mph). Or they want an L2 system with a top speed of 130mph. Most likely though they just want a Mercedes instead of a Tesla.

Waymo data from Phoenix showed a very different distribution from human drivers. In 6 million miles only 30 of least severe category (real and counterfactual simulation) and 8 with airbag deployment. Also note that there were zero collisions that did not involve another human...

Why not use Tesla’s 1 per million mile metric? Severe collisions are what really matter. Talking about collisions that are equivalent to curb rash just confuses things. The evidence shows you can’t extrapolate from L4 collision rate to severe collision rate.

Are you saying there are collisions Cruise didn’t report? How many L4 collisions did they have? Not even sure what point you’re trying to make by bringing up L4 collisions.

Robotaxis will not have any L4 collisions so they’re not relevant.

Not very useful for robotaxi safety because the distribution might be completely different (it is for Waymo).

I think @Doggydogworld is correct. You can look for notable Cruise and Waymo collisions on the DMV website and they're not there. The data for deployed vehicles is here...

I predicted it would never happen. Nobody will ever release a competitor to FSD (supervised) in the US.

"12.4 has almost completely retrained models. The final touches are for comfort" giving me big regression vibes. I feel that FSD progress should really be the march of 1's, the binary number system is more appropriate for computers and will let us better gauge progress. We've already got two 1's...

Our original bet Jul 15th 2022. Stock price $240. You knew it would be years of failure and yet did not sell. Sad! End-to-end will get the first nine and send stock to the moon. Bet is still on for 12.5?

They lay off the supercharger team before this “validator”? SMDH

Yep,"in any manner", they definitely should have reported it according to the law. Looks like there is a proposal to make traffic violations reportable. https://digitaldemocracy.calmatters.org/bills/ca_202320240ab3061 Frankly it seems just as likely the FSD is causing a bunch of unreported...

I like the panel alignment hypothesis. 1 cm accuracy explains a lot! :p Luminar says "This was offset by sensor sales to Tesla, which was our largest LiDAR customer in Q1 and comprised more than 10% of our revenue in the quarter." That doesn't preclude that much of the revenue was from...

Doing that software validation is the most secure job at Tesla. They’ll be doing that for a few more decades so they never have to give refunds. :p

So probably about 20 million miles per year with passengers. It would be interesting to know how many times they broke the law but I’m not sure it’s very useful for determining safety. Near collisions would be much more interesting (and if those were a result of breaking the law).

It’s also very easy to recognize a Waymo vehicle driving autonomously, they look funny and have no driver. I’m not sure I’ve ever recognized a Tesla running FSD on city streets (other than Alan’s). I need to look more carefully now that more people are using it.

A drivers test is only 20 minutes. I suspect the vast majority of people would fail if the drivers test was the worst 20 minutes of their driving history. Obviously we should include causing third party collisions when measuring safety. I would hope that Waymo is required to save data so that...

I don’t think they matter much. Being much safer than the average human driver is what matters to me. I’m sure there are many AV designs that could pass drivers tests but it doesn’t mean much because those tests are designed for humans. The only known way to test AVs is by brute force.

Not sure I agree with Chuck’s conclusion here. They’ve obviously never gated a release on the success of this turn.

Not sure if impatient is fair. They’re driving in LA, they could literally be waiting there for hours. I’m wondering how far they drove the wrong direction and whether it knew no one was coming. Technically you’re always driving against traffic when making a turn like that.

Waymo has to report when they hit dogs (or anything else). https://www.dmv.ca.gov/portal/file/waymo_052123-pdf/

Looks like their collisions are about the same. 71 in 2022, 50 in 2023 and 14 (x3 = 42) so far this year. Though I didn’t look to see if how many are with a safety driver driving (safety drivers seem to get in dumb low speed collisions).

That would be a horrible metric. So we deploy AVs and the number of fatalities increases? If I’m a passenger an AV I don’t care whose fault it is when it crashes. Highways are easier for L3 if it’s just a traffic jam assist features. I’m skeptical that they’ll get full speed with no lead car...

Highways are simpler most of the time. The problem is the times when there are pedestrians on the highway or there is someone driving the wrong way or there is who know what falling off vehicles or overturned trucks. Trying to get 100 million miles between fatal collisions with all the crazy...

anti lock brakes are required because they allow you to turn with brakes fully applied. When they were first developed I don’t think they even decreased stopping distance (because they didn’t modulate all the wheels separately and they had slow modulation) I don’t think they’ll ever require...

More evidence Waymo is cranking up the temperature on the neural nets these days (assuming this is new). It does seem like we're seeing a lot more Waymo fails than we used to. I assume it's because they're doing way more miles.

Interesting. It does seem like it must have been specifically programmed to turn there. I doubt it turns left at normal no left turn signs (otherwise we’d see video of that since they’re much more common than no left turn except for specific vehicles)

There is a signal there for a protected left turn. It’s too bad we’ll probably never get an explanation. Would be interesting to see how they screwed it up. My guess is that it’s a mapping error but it does seem like it must be recent even though nothing on the street has changed.

Interesting. Hopefully Waymo will explain. I suspect that Waymo thinks they are allowed in transit lanes but did not program in this exception.

SFMTA says taxis are allowed in the lanes. https://www.sfmta.com/muni-tips-using-transit-lanes#:~:text=Transit%20lanes%20are%20lanes%20that,such%20as%20Lyft%20and%20Uber. Waymos are taxis.

Sounds like @AlanSubie4Life is the only one generating interventions these days. Will they need to extend the free trial to get more data?

Tesla is much less worried about you suing them than they are about the person you hit suing them. While you could agree to pay Tesla’s legal fees it’s unlikely your pockets are deep enough.