Welcome to Tesla Motors Club
Discuss Tesla's Model S, Model 3, Model X, Model Y, Cybertruck, Roadster and More.
Register

FSD Beta 10.69

This site may earn commission on affiliate links.
I've used FSD often at night in suburban, rural and cross country interstate settings without cabin camera issue. 2021 M3. Maybe you have a camera issue that needs checked by the service center?
I have had FSD alternate between engaged and disengaged multiple times on one very dark well marked 50 mph country road with multiple warnings. In one instance I had a PS&S (phantom stop and sit) There was no traffic so I let it sit for about a minute before hitting the accelerator. Edit: This was 10.12.2 as it is all I have.
 
Violating my self-imposed gag on further comments; I am surprised this is resulting in confusion….Fairly sure that she is referring to the ventilated seats.


It was 1/2 second in the recent video which seems pretty poor but probably there’s not much incentive for them to reduce latency there. Hopefully control is much faster than that!


Friends do not let their friends drive them anywhere with FSDb; no surprises there at the moment.
Yes, you were finally 💯 % correct about something 👏!!
The air blowing in her butt was the front seat air vents!!
 
I worry that a major underlying unsolved problem is latency or delay in decision making and control. This may be a root cause of a number of bad behaviors — moving into an intersection or roundabout with conflicting oncoming cross-traffic, missing certain turns, braking too late around people entering crosswalks, excessive timidity entering signed stops as it tries to hide or deal with the latency, etc. It may also contribute to jerky and sudden control changes as it makes up for lost time by making sudden sharp turns.

It’s unclear to me if they can find a fix for this without faster compute hardware.

It's also possible the low resolution of the cameras (only 1280x960) means that recognition and classification of imagery cannot occur at far enough distances as it's too coarse compared to good human fovea vision, meaning that reaction is too late. Better cameras aren't a problem to install now, but it would greatly increase the data rate into the neural networks and that requires significantly faster compute which is a big issue.

Faster compute without the most efficient chips means high expense and high power consumption. I wouldn't be surprised if the Waymo cars have $10-20K of compute and 4000 watts of power consumption, which would obviously kill efficiency. It would be like resistive heaters running at full blast. And in the summer that would have to be A/C'ed out too.
 
It's also possible the low resolution of the cameras (only 1280x960) means that recognition and classification of imagery cannot occur at far enough distances as it's too coarse compared to good human fovea vision, meaning that reaction is too late. Better cameras aren't a problem to install now, but it would greatly increase the data rate into the neural networks and that requires significantly faster compute which is a big issue.

Faster compute without the most efficient chips means high expense and high power consumption. I wouldn't be surprised if the Waymo cars have $10-20K of compute and 4000 watts of power consumption, which would obviously kill efficiency. It would be like resistive heaters running at full blast. And in the summer that would have to be A/C'ed out too.

I wish they would update the cameras. My $20 security cameras have amazing nighttime imagaing with near no light. I actually keep the IR off and I get near daytime quality in full color.