Remus
Active Member
Bravo Tesla! This is big data at work ladies and gentlemen.New Tesla Blog: More Advanced Safety for Tesla Owners
Bravo Tesla! This is big data at work ladies and gentlemen.New Tesla Blog: More Advanced Safety for Tesla Owners
I think Tesla has set its system up for solving every 9 of accuracy to take slightly less staff time and slightly less annotated data than the previous 9. However, every 9 will require a 10x larger fleet to experience enough rare incidents to collect enough data to solve them. This is because for example if the first 9 required data collection, software and training to solve 1000 scenarios, you can solve the next 9 by solving another 1000 scenarios which are on average 10x less common. Every scenario should require a fixed number of annotated training examples and hence staff time to solve. The reason each 9 takes slightly less time than the last is because as the system builds up a larger and more varied set of scenarios, its solutions get more generalised and solving one problem is more likely to improve accuracy on a different problem.
Right - they are basically solving for accidents (or mistakes) per million miles. This is where it becomes increasingly difficult to figure out what are the next top 100 cases to solve. They get a lot of disengagements / shadow errors from the fleet. Millions every day. How do they analyze and then synthesize the data without watching each video and manually categorizing ?Note the 9s that Tesla is solving for are not image recognition accuracy. It is something more like probability of avoiding a shadow mode discrepancy/disengagement/accident per mile. This accuracy will be far higher than individual image recognition accuracy because sensor fusion and driving policy both compensate for weakness in the more granular image accuracy rates (particularly if camera & radar accuracy probabilities are independent).
Yeah I figured not.
But there is always tomorrow!
What we're seeing as current FSD, and what is future FSD shown during the investors day, are two different generations of software that sure, have the same origin, but targets are wildly different, and some approaches to problem solving have diverged for sure.I can't argue with that. I have 2018 Model X 100D with FSD and Navigate on Autopilot will surely get you in accident or worse if you don't keep an eye on it. My hope is that they are holding out the "good stuff" that EM is talking about and we will get that sometime this year and it will be much better than the current iteration.
Sorry about the link...someone else posted the fixed on.
True - rural (and even exurban) areas will need personal vehicles. BUT, the question is with potentially much reduced volume, is it possible they will continue to get inexpensive vehicles to buy. May be they go back to horsesOT
Oh, don't get me wrong -- the world went car-crazy in the 1950s and that's reversing. We may get back to the personal-vehicle-ownership rates of the 1890s. However, personally owned vehicles are certainly not becoming obsolete. In rural areas, no credible alternative to personally owned vehicles has EVER been proposed. Rural areas will continue to exist.
People talking about "transportation as a service" as if it's going to take over everything and replace personal vehicles have, uniformly, never lived in a rural area. It's an eyerollingly dumb idea for someone living on a farm. The logistics and economics of it don't work.
(In the old old days, your personal vehicle doubled as a work vehicle, and was called a "horse")
1/ Notes from the $TSLA call with deal underwriters. Elon and Zach on call, Elon did most of talking. The gist of the call was that autonomy is the key to the Tesla story "this is the transformative element...this is how $TSLA becomes $500B market cap company" - Elon
2/ Elon - "magnitude of this is hard to overstate". Autonomous cars will generate $150-200K of gross margin. Says regulators will want to see billions of miles of data that show that autonomous is safer than manual to approve it.
3/"We don't expect to spend this capital, want to have it as a buffer" - Elon
Zach reiterated guidance for Q2 and the year
"We think service quality is generally quite good, except for collision repair." Elon
4/ Will make decision on Model Y factory in next week.
If in Fremont, will add another tent and convert some inventory space to production.
Also claimed they will expand paint shop south to do more volume. Anyone seen any permits for this????
5/ Started taking orders for UK recently. Will open up other RH drive markets soon. Expect RH drive cars to begin shipping in next few weeks.
Sees opp to grow demand in US states where there is little or no service capacity at present.
6/ Says S&X demand up since refresh, claims Q1 orders weak because people knew the refresh was coming..
Elon: "Tesla's like the leakiest company on Earth"
7/ Elon claims Panasonic relationship is "pretty good...a little disappointed they haven't reach full capacity yet"
Working to bring on other suppliers in China, don't want to be cell constrained again.
SomeHey, you remember all of those short theories about Elon being a hair's breadth from a margin call due to owing surely a billion dollars (at least!), and this spelling the imminent doom of Tesla?
Yeah, about those theories...
View attachment 403255
I haven't been following this but is there any consensus on the short term? Up or down? My home buying aspirations are hoping back up to a reasonable level soon. BTW, home prices in this part of the SF bay area are tumbling quickly, not sure what that says for the economy. The housing market was crazy a year or so ago with huge overbidding and all cash or forget about it.
One of the shorts took notes of the CC with investors arranged by Govt Sachs. I have edited out the ad hominem :
Personally thrilled about the highlighted part
Somedeersbears got caught staring at the headlights today
View attachment 403520
What time was that call at?
Well, actually DHCP....Unless you have a static set of IP addresses, like I do, IP addresses change due to NATing.
Yes, I hope 231 is the lowest we'll see this year. BTW, in the last 2 years, after ER when the SP falls, it has hit the minimum within 4 trading days.The best solution would be to see a few days of nice climbing, because when volumes are high and the stock price is rising, the shorts tend to lack the horsepower to reverse.
I’d prefer to pick my horn sound from Fart Mode.
My theory is he found gold in a boring tunnel.Regarding the margin loan, my theory is Elon might have liquidated some of his spaceX non voting stock. SpaceX valuation was consistently increasing, and it has dual class shares.