PACEMD
Active Member
Thanks, Alan. No known spills/pee but gives me some direction.
-
Want to remove ads? Register an account and login to see fewer ads, and become a Supporting Member to remove almost all ads.
FSD v12.x (end to end AI)
- Thread starter Buckminster
- Start date
-
- Tags
- #fixphantombraking 12.4.x is coming autopilot chill is not chill elon is an ass elon rocks fix fsd extreme late deceleration fsd does not commit to go fsd does not maintain proper speed fsd doesn't read signs properly fsd hard and late braking fsd has decision wobble fsd jerky driving fsd late deceleration fsd sometimes may not detect train crossings fsd stops too early too quickly fsd stops too far behind line fsd stops when there is zero visibility fsd tailgating in city streets fsd very slow at stops fsd will never enable l3 with hw4
sleepydoc
Well-Known Member
Anyone have a sketch or diagram of an inline V6?
I was quite confused by the SAE wording for a while, as it seemed to me that L3 should allow catnaps because I'm pretty sure I could be awake and competent to take over within about 3 seconds of being alerted to do so, even if asleep initially. But I respect the "no sleeping" rule for L3 now, it would be just too potentially messy otherwise.
sleepydoc
Well-Known Member
Agreed, although could a remote user connect to the car and figure out what was going on any faster than someone that just woke up from a nap? Probably not but that also makes the assumption that all level 3 systems and uses are equivalent. I think initially when the need to intervene is more likely a 'no sleeping' policy makes sense. Regardless, any system should be able to safely stop the car if the driver doesn't respond for whatever reason.
Daniel in SD
(supervised)
Speed limits are also made up numbers...
I think 10 seconds is the UNECE regulation.
I think this refers to things like the car being on fire. Which should be detectable by someone in the car but not by the car itself.
AlanSubie4Life
Efficiency Obsessed Member
Looks like they are going for the second 9.
Remember this is the version Elon saw which made him go for Robotaxi paydirt.
I literally just got that fixed under warranty. My 2019 Model 3 started inconsistently throwing that fault - the service notes say they found the seat was pinching the wiring harness for the seat belt pretensioner and they replaced it for free (out of warranty by a little bit too).
I'd suggest putting a service request, especially if you're under 60k miles and the supplemental restraint system warranty should cover it.
If you go into service mode it may show more details about what component specifically has the fault, if you're curious.
It's probably a good idea to fix it. Seat belt pretensioner failure in a crash would make the car less safety (maybe a lot less safe, I'm not sure)
Oh, not me. It took me 15 minutes to get out of bed this morning.
Joking aside, I'm highly skeptical we ever see wide rollouts of L3 systems with these short 10-15 second takeover times. Humans are bad drivers already under normal conditions, let alone acquiring situational awareness within a few seconds. Slightly more likely, IMO, is a system with a strong enough safety record that the manufacturer would be comfortable with no driverless operation on highway and the only L3 handbacks are triggered at off-ramps where there is no time pressure.
Silly bear, it's just two of V6 laid out in a row.
Which is how we get V12 End-to-End!
This info comes from the Tesla Institute of Technology
FSDtester#1
Large Member
PACEMD
Active Member
AlanSubie4Life
Efficiency Obsessed Member
One addition here about the no safety regressions, they are just double confirming that and then they are good to go. OMG, this is it, the first 9.
And much smoother! Remarkable. I thought there was a distinct group of people here who said it had no smoothness issues.
And no I don’t think it will be smooth and I don’t think it will be particularly good, but I am betting on the first 9 this time.
Though that is extraordinarily dumb (it’s me after all), because past experience has shown that none of the point releases result in any changes to driving behavior (it’s not retrained AFAICT). So really it should be 12.5 which does it. Though maybe they can prompt-engineer it to make it “Faster” “Make it really fast”, etc. since that is all that is needed. 3-second crossings should do it.
And much smoother! Remarkable. I thought there was a distinct group of people here who said it had no smoothness issues.
And no I don’t think it will be smooth and I don’t think it will be particularly good, but I am betting on the first 9 this time.
Though that is extraordinarily dumb (it’s me after all), because past experience has shown that none of the point releases result in any changes to driving behavior (it’s not retrained AFAICT). So really it should be 12.5 which does it. Though maybe they can prompt-engineer it to make it “Faster” “Make it really fast”, etc. since that is all that is needed. 3-second crossings should do it.
Last edited:
Just for science, been experimenting how FSDS misreads certain small road signs for speed limit signs. 45 mph speed limit drops to 20 at a certain sign 100% consistently.
Put tape at different places on the zero to see if that would throw it off so FSDS would ignore the sign. No joy, speed would drop still, usually to 30, but varied.
Suddenly, last 2 times it has ignored the sign meaning speed limit properly remained at 45 mph!!!!
Perhaps there was a mapping change I was not aware of just recently? Or…..
somehow FSDS has the ability to make small adaptations? Seems very unlikely.
Now I have to remove the tape to complete the experiment before 12.4.2 drops to observe how it reacts. If it is mapping then it will remain fixed, if it reverts to 20 mph at the sign then that will be very interesting.
Put tape at different places on the zero to see if that would throw it off so FSDS would ignore the sign. No joy, speed would drop still, usually to 30, but varied.
Suddenly, last 2 times it has ignored the sign meaning speed limit properly remained at 45 mph!!!!
Perhaps there was a mapping change I was not aware of just recently? Or…..
somehow FSDS has the ability to make small adaptations? Seems very unlikely.Now I have to remove the tape to complete the experiment before 12.4.2 drops to observe how it reacts. If it is mapping then it will remain fixed, if it reverts to 20 mph at the sign then that will be very interesting.
willow_hiller
Well-Known Member
Perhaps there was a mapping change I was not aware of just recently? Or…..
I think there may be some sort of automated or rapid map adjustment mechanisms. On V12 I've had a couple of incorrect lane choices that have occurred exactly once. One mistake, one disengagement and voice report, and then it's never made the mistake again.
gottagofast
2022 Model 3 Performance
The county just repaved the suburban four lane divided highway by my house. There are sections with no markings on the asphalt. FSD didn't even blink. It still visualized the lanes, including turn lanes, and kept its lane like always.
nonStopSwagger
Member
When you say it's coming, I wasn't sure if you meant it was going out to Tesla internal testers, Tesla regular employees, YouTube influencers, or the general FSD owners, - "going wide". Which one is it this week? Asking as I have road trips starting Thursday.
