-
Want to remove ads? Register an account and login to see fewer ads, and become a Supporting Member to remove almost all ads.
Wiki FSD Beta 10.4
- Thread starter MilesAR
- Start date
CaptUAL
Member
There’s always one to bugger it up..
Attachments
jebinc
Well-Known Member
Right. I first started with the email, but figured that would take forever, so a seek a faster method to undo this. No change to firmware yet… tick tick tick…. Maybe I’ll be unenrolled in “two weeks,” or “soon”…
MarcG
Active Member
I live in San Francisco, and in my experience 10.4 has been a step back. In the last 24 hours, my car tried to run 3 red lights! Once even after it was fully stopped. And the red lights were super obvious, not to mention ones where the car has stopped on red in previous FSD builds.
I’m in the East Bay and just became a beta tester with 10.4 ~3 days ago. It is generally worse than I had imagined given that I’m in the Bay Area, although it has also done some really impressive stuff. Good to know that 10.4 is hopefully just a temporary blip in progress. So far, driving is kind of a cross between a drunk teenager at the wheel and a roller coaster with some relaxing moments in between! Either way, I’m excited to be a
Beta tester.
I have never used the brakes in 3 years of ownership more than it’s been used in 3 days of FSD driving on AP.
To be fair in night driving, with well marked roads with reflectors and clear lanes painted, it does really well.
TravelFree
Active Member
Show me that the AI you believe is real ( maybe just immature) is not just a bigger faster calculator that operates on a library of rules ie. equations. I don't drink coffee and never needed drugs to learn. But I do know Fortran so I have an elementary understanding of computer programming. Just show me how AI is not just a very fast very robust calculator that is silicone hardware using software to decide what to do.
Absolutely not! The human brain takes in visual, touch, and sound sensory and the brain creates moves based on a biochemical - electrical reaction. The top scientists barely understand how it works. There are rules but how the brain applies those rules is where the human brain differs from a set of instructions stored in memory. Why does a human brain decide to run a red light. Will the AI in a Tesla be that creative? Ok the programmers have already decided to write an instruction to allow the FSD-beta to coast through a stop sign. You may think that is OK because you do it all the time. But did AI decide to do that or did a programmer write that instruction for the FSD calculator to follow?
I'm not saying we will never have true artificial intelligence that can invent, create, and decide to destroy the human race as an inferior lower lifeform. It could be possible, Will we create that level of AI? Or, just a faster bigger computer than can calculate faster.
One of the problems the current Teslas all have with these left and right turns is seeing around a corner. The location of the pillar cameras is too far back which requires the programmer to write an instruction to cautiously creep into the cross traffic until the cameras can see left and right. Fort FSD to be better than humans it needs to locate the cameras up near the headlights. One YT'r already tested this and was able to see approaching traffic that the pillar cameras could not so those cameras instructed the car to creep into the lane of traffic. The tester had his GoPro mounted on the front of the car with it's remote view could see what the pillar cameras could not. This is not original because we have our own robo bus in town that puts it's cameras up near the front left and right on the front headlights.
I considered what you wrote about the blind person being able to see... but all you did was confirm what I said and that is FSD beta is nothing more than a special calculator with a software program that runs very fast. If true FSD needs to know every possible scenario that will ever happen and compute that faster than a human. The hardware we are putting in the cars today are grossly inadequate. Even Musk claims he is striving for the march of 9's and at some point he will decide it is good enough. But will the regulators? The Musk march of 9's will be adequate when statistics tell him Tesla FSD is safer ( fewer accidents) than human drivers. I agree that may be good enough. BUT, is that true AI? I don't think so. We're a long long way off from the thinking liquid metal robot in The Terminator.
You can believe in the fantasy of a Robotaxi that can think and go transport people anywhere anytime perfectly, mixing in with human drivers. All I see possible is a better Level 2 FSD / NOA that I will need to monitor but make make the mundane steering and speed done by a machine. I don't expect to live to see the day when I can get in the back seat and say take me to my sister's house in Pennsylvania and then I take a nap or watch a movie.
TravelFree
Active Member
I hear ya! I watch quite a few YT FSD beta videos and take note on all the failure cases demonstrated. So far I have limited my testing to drives that I know have not been demonstrated as failures with high frequency. Left and right unprotected turns and construction zones. There is no need for me to turn it on as I know it is not going to pass and be safe. 10.4 now has been 99% perfect on stop signs and speed bumps. 10.3 was a complete disaster with these. High traffic areas are really dangerous around here with so many drivers quick lane changing and running red lights. FSD beta just doesn't react to illegal driving activity.
I don't use FSD beta as a tool, rather I do my FSD testing as a test drive. I'll let others repeat failures over and over if they want.
TravelFree
Active Member
You don't need to opt out. Just set up a separate profile for FSD-beta and set the menu settings as desired. In your original profile, go into the autopilot and turn off the selections that are for the FSD beta. Don't use AP off the highways. On the highways, it will resort to your original NOA AP. Works for me.
This may change when they go to single stack but right now the above works well.
He/she wants to get the latest/regular/standard firmware (example 40.x) updates for the car.
Reddy Kilowatt
Active Member
i may have missed it, but where do these curbing events happen? While turn left? Right? Or simply driving down the road?
I just bought two new rear tires and there not cheap. Tesla doesn’t offer road hazard protectio. That was a mistake on my part?
my like was ment to be informative
Reddy Kilowatt
Active Member
how Do we report issues to Tesla. Bug report? , press the camera icon? I missed something somewhere.
This not true.
I’ve tried to disable FSD automatic lane changes many times in Navigate on Autopilot settings but that had no effect on FSD. FSD automatic lane changes cannot be turned off.
TravelFree
Active Member
It only works on highway driving but not in city or off highway turns. The whole idea of FSD beta on city streets is it makes turns automatically. If you don't want to test FSD beta on city streets then just disengage FSD beta / including AP while driving off the highway.
I suggest you set up a separate profile- call it "FSD-Beta" then select the appropriate menu settings. Go into your own profile and disable FSD-beta.
TravelFree
Active Member
Yes, Chuck Cook has reported this flaw to Tesla for several months. That flaw still is not written into the code. If this were truly AI the car's FSD computer would have figured it out on it's own. Look up Chuck Cook's You Tube videos.
TravelFree
Active Member
VRU?
My ignorance so I researched this- It is "Vulnerable Road User" Refers to pedestrians and bicyclists who enter moving traffic on the roads placing themselves at risk of being mowed down as "road kill." It is described in the release notes but I didn't understand how Tesla got VRU from a Pedestrian.
My ignorance so I researched this- It is "Vulnerable Road User" Refers to pedestrians and bicyclists who enter moving traffic on the roads placing themselves at risk of being mowed down as "road kill." It is described in the release notes but I didn't understand how Tesla got VRU from a Pedestrian.
Knightshade
Well-Known Member
Tell me you don't understand what a neural network is without saying you don't understand what a neural network is.
See above.
NNs are often called black boxes for this exact reason.
Could be either.
Just like "a human wrote the law about stop signs that a human driver may or may not follow depending on other circumstances"
Now, you certainly COULD hard code the computer to NEVER run a stop sign no matter what- that's how the original system worked... but as more decision making moves to NNs that will be less and less the case over time.
How does the programmer know when it can see left and right well enough and when it can't? Specifically?
How does it know there's a bush in the way or not? Specifically?
What is the hard code that tells it that?
(Spoiler- there isn't any- perception is done with neural nets- not hard coding)
FWIW I agree it needs further-forward side/facing cams for this purpose.
But that has nothing whatsoever to do with hard code vs NNs, it has to do with the physics of light and vision.
So funny story to again drive this point home.
Computers designed to play Go, for years and years, using traditional hard code- couldn't beat anybody but low-mid grade tournament players.
Once they switched away from hard code to neural networks they soon began beating world champions.
And much like Chess (which has also moved to using NNs at the top levels of play) the NNs often produce moves unusual and surprising to humans, but which consistently beat said humans.
Again- I agree we need both at least 2 more cams as mentioned, and more computer (Is HW4 enough? I dunno- neither do you, neither frankly does Elon- we won't know it's enough until it's enough)
But the regulator thing is entirely a red herring.
It's already legal to operate an L4 or L5 system in a number of US states. Today. With no additional permission/certification needed from regulators.
That's a question for philosophers.
But what it's definitely NOT, even today, is just hard code running fast.
Knightshade
Well-Known Member
BTW- I used 10.4 last night for a trip from home to a friends house in Durham, roughly 30-35 minutes away...
Going, due to an accident on the interstate, it routed me on all local roads... a few stop signs, a few lights, fair # of intersections... mostly 1 lane each way, with a few being multilane roads.
FSD did the entire trip with only 1 intervention (but 0 disengagements)... and that wasn't strictly needed.... there was an unprotected (well, flashing yellow arrow) left, and the car was being overly cautious, passing up 2 gaps I'd have taken, so eventually at the next gap I gave it a bit of accelerator and it drove through it.
Trip home was via interstate (a few miles on local roads at each end)- 0 interventions or disengagements at all... but it was after midnight so very little traffic.
The local roads section did have some light phantom braking- and one FCW as it came over a hill on a bit of a curve and there was an oncoming car (though both my car and the other were properly in their lanes with no collision concern at all).
Also it failed to slow adequately for a couple mild speed bumps near my friends house... (took them at 25- so not omg car damage, but I'd have certainly slowed down a bit more.)
It works AWESOME when there's not many other cars
It actually worked fairly well with some cars on the way there- but several times it was clearly doing so slowly enough it was annoying to some drivers, this was most obvious at intersections- and I wanna say as in my post above, a couple of more-forward side cameras would go a long way here, but even when there was no visibility issue and clearly no other cars it was slower to make a turn than I'd have been- might have to try the aggressive setting next time.
Going, due to an accident on the interstate, it routed me on all local roads... a few stop signs, a few lights, fair # of intersections... mostly 1 lane each way, with a few being multilane roads.
FSD did the entire trip with only 1 intervention (but 0 disengagements)... and that wasn't strictly needed.... there was an unprotected (well, flashing yellow arrow) left, and the car was being overly cautious, passing up 2 gaps I'd have taken, so eventually at the next gap I gave it a bit of accelerator and it drove through it.
Trip home was via interstate (a few miles on local roads at each end)- 0 interventions or disengagements at all... but it was after midnight so very little traffic.
The local roads section did have some light phantom braking- and one FCW as it came over a hill on a bit of a curve and there was an oncoming car (though both my car and the other were properly in their lanes with no collision concern at all).
Also it failed to slow adequately for a couple mild speed bumps near my friends house... (took them at 25- so not omg car damage, but I'd have certainly slowed down a bit more.)
It works AWESOME when there's not many other cars
It actually worked fairly well with some cars on the way there- but several times it was clearly doing so slowly enough it was annoying to some drivers, this was most obvious at intersections- and I wanna say as in my post above, a couple of more-forward side cameras would go a long way here, but even when there was no visibility issue and clearly no other cars it was slower to make a turn than I'd have been- might have to try the aggressive setting next time.
Similar threads
