Welcome to Tesla Motors Club
Discuss Tesla's Model S, Model 3, Model X, Model Y, Cybertruck, Roadster and More.
Register
This site may earn commission on affiliate links.
The next big milestone for FSD is 11. It is a significant upgrade and fundamental changes to several parts of the FSD stack including totally new way to train the perception NN.

From AI day and Lex Fridman interview we have a good sense of what might be included.

- Object permanence both temporal and spatial
- Moving from “bag of points” to objects in NN
- Creating a 3D vector representation of the environment all in NN
- Planner optimization using NN / Monte Carlo Tree Search (MCTS)
- Change from processed images to “photon count” / raw image
- Change from single image perception to surround video
- Merging of city, highway and parking lot stacks a.k.a. Single Stack

Lex Fridman Interview of Elon. Starting with FSD related topics.


Here is a detailed explanation of Beta 11 in "layman's language" by James Douma, interview done after Lex Podcast.


Here is the AI Day explanation by in 4 parts.


screenshot-teslamotorsclub.com-2022.01.26-21_30_17.png


Here is a useful blog post asking a few questions to Tesla about AI day. The useful part comes in comparison of Tesla's methods with Waymo and others (detailed papers linked).

 
Last edited:
I think the intermittent wiper function on older S has been disabled once I installed FSDb, it doesn't matter whether I am on FSD or not, even after I disabled FSD, the intermittent wiper just never turns on until the camera thinks it is time to wipe. It's been raining non stop for a whole week and this afternoon is drizzle misting day, it should wipe every few seconds but it wipe probably once per minute, I guess the camera thinks it can see and no need to wipe it, but wait ... I also got a warning FSD function reduced because of poor weather condition, it's annoying when I have to turn on and off the wiper ... manual intermittent wiper, luckily I still have the stalk to control the wiper, this is so dumb.
 
Yesterday, on my extremely rural lane, with a course programed in, 11.4.4 stopped at a stop sign and appropriately said, "turning left." It turned right. After, I stopped it and backed up, turned around and proceeded to follow the route (and turned it back on). But HFJ.
Maybe 11.4.4 has been trained on data from my wife driving. "No, no, the other left!"
 
If you doubt it, and if you have your FSD car connected to your Wi-Fi, check the logs of your router. It's particularly easy if you have one of the routers or mesh systems that have an app for reporting and control.
The "data advantage" is grossly overhyped. If more data was the main solution to self-driving Tesla would already be the best by far. In practice they are at least three orders of magnitude away from being at par with the leaders and with no real visible meaningful progress towards even outpacing them in improvement rate. Instead the gap widens every year.

Why is that do you think?
 
  • Like
Reactions: am_dmd
If you doubt it, and if you have your FSD car connected to your Wi-Fi, check the logs of your router. It's particularly easy if you have one of the routers or mesh systems that have an app for reporting and control.

As I understand it, Tesla prefers to collect the data from cars when they're connected to Wi-Fi, typically at the owner's home while idle or charging. This is probably to control costs as you referenced; the owner's high-speed internet connection avoids cellular data charges to Tesla.​
The same is true regarding software update downloads to the car- the user's Wi-Fi connection is used if and when available, but Tesla can use the cellular Connection of the car if they decide the data transaction is sufficiently important or time sensitive (e.g. if they're specifically targeting certain training data through a data seeking "campaign", or if the car is involved in a detected accident, or if a software update is considered urgent due to a recall deadline or other critical bug fix).​

For the normal data transactions over Wi-Fi , you can easily prove to yourself that significant amounts of data are uploading. In my case, my eero app (for my mesh Wi-Fi network at home) shows 2.9 GB uploaded from the car just for October 29th, the first day of the new week - fairly normal in my experience. This despite the fact that I have taken only two modest and completely routine commutes over the past 24 to 36 hours. The download data size for the same date is 2.5 MB which I suppose is simply data traffic overhead, the data request commands from the Mothership, handshaking, error correction and so forth.
How about the agreement we accept at FSDb signup, is there data sharing? I don’t remember but def expect it is there.
 
Nightmare Before Christmas question: What will the Holliday update include?

  1. 11.4.7.1.1.1.1.1.1/11.4.4.1.1.1.1.1.1
  2. 11.5.x
  3. 11.69.x
  4. 11.420.x
  5. 12.x (the mythical)
I predict v11 beatings continue until FSD customer morale improves. 🧛‍♂️🎃🎅

I should add TSLA had it good for a long stretch but the worm seems to be turning given macro conditions, EV demand, digging grave with cybertruck, ongoing 4680 snafu, solar demand, gigaMexico, etc. One could imagine how FSD project cuts would play out.
 
Last edited:
The "data advantage" is grossly overhyped. If more data was the main solution to self-driving Tesla would already be the best by far. In practice they are at least three orders of magnitude away from being at par with the leaders and with no real visible meaningful progress towards even outpacing them in improvement rate. Instead the gap widens every year.

Why is that do you think?
Please provide data and/or statistical analysis to backup your claim of "three orders of magnitude" (1000x) behind other leaders, including who those leaders are, on what basis they are "leaders", and what measurements you use to compute leadership positions and/or self-driving progress.
 
Please provide data and/or statistical analysis to backup your claim of "three orders of magnitude" (1000x) behind other leaders, including who those leaders are, on what basis they are "leaders", and what measurements you use to compute leadership positions and/or self-driving progress.
Sure.

According to reports to the CA DMV Waymo has one disengagement per 17k miles driven (2022). In city driving Tesla has a disengagement ever 5-15 miles according to FSD Community tracker 2023. That's 1000-2000x.

If we only count critical* DE:s for Tesla they are at about 35 miles per DE, which would only be 500x worse than Waymo, but 1000x worse than the top reporters 2022.

So I'd say "three orders of magnitude" (1000x) is a pretty fair ballpark estimate all things considerered.

*) Avoid accident, taking red light/stop sign, wrong side of the road, unsafe action

Sources:
 
Last edited:
Sure.

According to reports to the CA DMV Waymo has one disengagement per 17k miles driven (2022). In city driving Tesla has a disengagement ever 5-15 miles according to FSD Community tracker 2023. That's 1000-2000x.

If we only count critical* DE:s for Tesla they are at about 35 miles per DE, which would only be 500x worse than Waymo, but 1000x worse than the top reporters 2022.

So I'd say "three orders of magnitude" (1000x) is a pretty fair ballpark estimate all things considerered.

*) Avoid accident, taking red light/stop sign, wrong side of the road, unsafe action

Sources:
But Elon has said it's safer than a human..... :rolleyes: 🤣
 
Yes, we all must remember the adage, “Never let the facts ruin a good story,” (aka, line of BS from a Charlatan). 😉

Reminds me - we should meet up and I can show you how my 3 performs in my usual routes. We can do the same in your routes - so we can figure out if the difference in experience is because of
- Expectations
- Difference between 3/S
- Different road conditions
 
Reminds me - we should meet up and I can show you how my 3 performs in my usual routes. We can do the same in your routes - so we can figure out if the difference in experience is because of
- Expectations
- Difference between 3/S
- Different road conditions
My car is pretty much unusable in West Seattle. When you’re free, you, me, and @jebinc should get together.
 
I should add TSLA had it good for a long stretch but the worm seems to be turning given macro conditions, EV demand, digging grave with cybertruck, ongoing 4680 snafu, solar demand, gigaMexico, etc. One could imagine how FSD project cuts would play out.
You are obviously new around here. Tesla has had much worse times and near death experiences multiple times. Demand has "collapsed" multiple times. Nothing new here.
 
I received a survey from Tesla yesterday which included many questions about my satisfaction with autopilot and FSD.

Upon completing the survey and submitting it, this is what it returned. Peak Tesla.

View attachment 986500It’s
The server filters feedbacks that have no negative response or no suggestions for improvement. I submitted my feedback without any problems. 🤣
 
Reminds me - we should meet up and I can show you how my 3 performs in my usual routes. We can do the same in your routes - so we can figure out if the difference in experience is because of
- Expectations
- Difference between 3/S
- Different road conditions
I think the plan was for you to meet with @wiliamg, as you both live in Seattle. I’m down in Covington.
 
I received a survey from Tesla yesterday which included many questions about my satisfaction with autopilot and FSD.

Upon completing the survey and submitting it, this is what it returned. Peak Tesla.

View attachment 986500It’s
I got this earlier today when trying to send a Google maps route to my Plaid (running FSD junk firmware).

pacific northwest oral surgery federal way - Google Search.jpeg