Search results

Fairly sure Tesla lawyers were involved in forming this opinion - I don't think this is Rohan's personal reading.

I don't see how this is a "hit piece". The NHTSA report isn't glowing and has serious downside potential for Tesla. Believe it or not, non-business press simply doesn't care about trading time or option expiring day etc.

Here is something we should all be discussing. May be needs a new thread.

I'm confused. You are saying you won't buy in a million years because you think FSD is static and won't improve for another million years ? Thats a rather pessimistic view (esp. considering you are so optimistic about your lifespan) ;)

Right - and safety too. Safety can cut both ways - you might feel safer in a car without a driver if you are traveling alone at night (esp. for women). Or you may feel safer with a driver if the drive is through not a good area where someone can mess with the car.

A good question is - why is the driver letting the car make that mistake in the first place. Isn't one of the ideas to disengage when it makes an important mistake - otherwise how will it ever get better ? I almost always intervene if the select lane will lead to a missed turn (or in this case...

But - for that they have to be actually better than uber etc. Currently (Waymo etc) are not. They are just a curiosity.

Actually - if you see all the crashes mentioned in the NHTSA filings, you won't find all of them mentioned by media. When a crash happens - some local media has to first report it. Then its picked up by national paparazzi / bait-click media for clicks. If locally it is not reported (or atleast...

I'm bringing into this thread - a comment made in the Options thread. It is more appropriate to answer that in detail here. For one thing as I've explained in this and V11 threads so many times - there are a number of issues with the way roundabouts were handled in V11. It would stop sometimes...

Dude ... I've been wanting roundabouts to work for years. I even have a separate thread on this in the AP sub-forum. So, stop with the BS exaggeration.

But they won't even allow FSD on the roads ;)

This has the potential for disruption (and I somewhat agree with this). It also runs counter to the pump SP is receiving because of all the attention on FSD. Unfortunately I sold 150 puts for next week before the slide started.

Neither of those statements are correct. About 1/2 the roundabout execution was fine in V11 (may be more if you ignored stopping at the roundabout when no cars were around). Now they are mostly ok - but I had to intervene atleast 20% of the time. I keep repeating this - but a lot of people are...

Can you do those "way more challenging" ones on FSD and see how it fares ?

Ten in a row at Cult's ULT ? Its not just about collision - its about doing it "right". Even when you make a mistake there may not be collision (as in that case) since the other guy will take preventive action.

You are confusing the two things. The above is not the same as what you claimed. All Elon is saying is that they know 3 to 6 months out what they have got. He didn't claim what they have got in 3 to 6 months is "robotaxi" candidates. You don't go from 1 disengagement in 20 miles to 1...

You were the one who came up with the idea Waymo ULT is great. I gave a counter example. Its for you to prove, their ULT is great, since you made the original claim. Its not for me to disprove you and you are not right until disproven ;)

Thats not what they said. "Yeah. In terms of scaling loss, people in the community generally talk about model scaling loss where they increase the model size a lot and then their corresponding gains in performance, but we have also figured out scaling loss and other access in addition to the...

Yes, Tesla should have made California stops an option with default being full stops.

Why not ? As long as a judge is willing to take it up ... anything can be contested in a court. If a judge is not even willing to take it up - then, in anycase you aren't likely to win.

I think so was mine ;)

Right - so, why not require Tesla to not speed ? Is there any data to backup NHTSA assertion that not completely stopping at red lights leads to more accidents ? I think there is enough data to prove speeding leads to more accidents ... We want govt agencies (and courts) to make decisions...

Cybertaxi will not be for sale.

Those are not violations - those are bugs ;) The NHTSA requirement is not to do a "California stop", which apparently is done all over the US. I wish Tesla took that to the court. Would be interesting to see what the court says - should automatic driving be held to a higher standard than...

The SP move up after a pretty bad ER looked to me like shorts covering after assuming Tesla has given up on lower priced models. The truth as usual is somewhere between Rueter's article and Elon's claim of "they are lying (again)". Tesla hasn't given up on Model 2 but has given up on new...

Because I don't know ... not sure anyone outside Tesla knows. BTW, I tried to figure that out using the mandatory filing of Tesla with NHTSA - but thats for all of AP/EAP/FSD. I've a thread on that somewhere ... ps : Here it is ...

Yes ... like this one I posted earlier. One Waymo cut the other one.

Without providing more data, that billion miles is pointless in terms of city driving. Give us the intervention rates - categorized. Thats the only way to judge FSD progress.

There are hundreds of examples of FSD taking tuns without curbing. That is the problem with autonomous cars - you have to be able to drive 100,000 miles before a serious accident. So its not about the times you get it right, but about the times you get it wrong.

I remember @diplomat33 claiming Waymo is great at ULTs ;)

All because of the Reuters article. That should teach the leakers. I sold 175 calls just before the close. Let’s see if they are in danger.

Boston is an edge case.

There will always be dumb people - you can't use that excuse to not publish hard data when you claim you are going "balls to the walls". You want people (and investors) to take your claim that you are getting closer to achieving robotaxi level FSD - publish data. Otherwise its just BS. Whatever...

Time, rather than money ?

Is this your first vehicle ? BTW, you are in London - so did you really buy FSD ? Or is it some town called London in US .....

One contrary thing to remember is - as FSD figures out how to handle one thing, we figure the next thing. For eg., earlier I'd just disengage in construction areas. Now that V2 handles it somewhat ok, I let it go - but usually end up disengaging because of some particular issue. So, FSD has...

Couple of interesting things happened today. First I had a near accident. For once, it wasn't FSD trying to rush into roundabout when another car was coming. Some driver next to me on the left lane realized late that he needed to turn right and without looking tried to change lanes. He was a...

So, 11 interventions in 75 miles or about 1 in 7 miles. That sounds about right. That is what we have been seeing for a while now. BTW, if you haven't seen this ... here is a crowdsourced intervention rate. https://www.teslafsdtracker.com/Main

If they don't that is because they are not good. If they claim they are "close" to robotaxi but disengagement rates are 1 in 20 miles (vs Waymo's 1 in 10,000), investors are going to laugh. Thats why Tesla doesn't publish hard data now. If and when Tesla starts getting really good disengagement...

What does that even mean ? Just gibberish ...

Right - its the pace of improvement that we need to figure out. Without that - its all speculation. Specifically I want Tesla to publish categorized hard data on interventions/disengagements. We need to be able to tell the change of that metric by release. If Tesla is willing to do that - it...

Why would that be ? They would have used all the data they collect from all vehicles. Employee vehicles would only be used for validation.

Yes - more specifically - with V10, V11 we saw that FSD hit local Maxima and didn't improve significantly for a long time. Why would it be any different this time - or more accurately what will be the proof that it is same or different this time ?

Really ... ? I remember last time - some were predicting bottom in the 80s ...

Didn't you say this before last ER ? ;) I just hope SP doesn't fall to 100 after ER. I'm not ready for that.

Actually for years people have speculated a secret FSD version that is much better. Given how much Elon would love to solve FSD (and how he had to eat humble pie year after year), I doubt they have anything better. Moreover - they simply don't have any training data for the new robotaxi (with...

What is unknown is how long will it actually take - year+, 5 year+, 10 year + .... ? Nobody knows. For eg. how long will it take for Tesla to recognize/respond to school bus and school zones ? Surely they have enough training material. It isn't an edge case and very easy to gather more training...

Lots of times. FSD will either wait or squeeze through if there is enough space (and the cyclist is not riding the white line). Infact have you ever heard of FSD hitting a car coming from the other direction to pass a cyclist ?

Its the same thing with cutting yellow line when turning. FSD won't cut the line and hit a car if its standing there. Same with humans. (obviously with exceptions). Its the same with crossing the middle yellow line when driving because of some obstruction / bike - FSD won't do it if there is...

I'd compare FSD to an inexperienced, anxious driver. But might still pass the driving test ...