14.3.x is broken. The phantom braking is getting out of hand. The attention monitoring is stricter. I've been manually driving a lot more because FSD is just so unpredictable on this version.
Cybercab action at Giga Texas today with over 40 in the outbound lot, many at Crash Texting (likely disposing of older engineering versions no longer needed) and Cybercab production body parts stands on the N end of the main factory.
๐จ JUST IN: Christianity is SURGING among Americaโs Gen Z, a TON of young people just got baptized
Reports indicate a HISTORIC pro-faith shift among the youth
Huge news for the future of America! ๐๐ป๐๐ป
BREAKING: Tesla has officially released FSD V14.3
I'm downloading it in my Model Y right now. Here's everything that's new:
โข Improved parking location pin prediction, now shown on a map with a P icon.
โข Increased decisiveness of parking spot selection and maneuvering.
โข Rewrote the Al compiler and runtime from the ground up with MLIR, resulting in 20% faster reaction time and improving model iteration speed.
โข Enhanced response to emergency vehicles, school buses, right-of-way violators, and other rare vehicles.
โข Mitigated unnecessary lane biasing and minor tailgating behaviors.
โข Improved handling of small animals by focusing RL training on harder examples and adding rewards for better proactive safety.
โข Improved traffic light handling at complex intersections with compound lights, curved roads, and yellow light stopping - driven by training on hard RL examples sourced from the Tesla fleet.
โข Upgraded the Reinforcement Learning (RL) stage of training the FSD neural network, resulting in improvements in a wide variety of driving scenarios.
โข Upgraded the neural network vision encoder, improving understanding in rare and low-visibility scenarios, strengthening 3D geometry understanding, and expanding traffic sign understanding.
โข Improved handling for rare and unusual objects extending, hanging, or leaning into the vehicle path by sourcing infrequent events from the fleet.
โข Improved handling of temporary system degradations by maintaining control and automatically recovering without driver intervention, reducing unnecessary disengagements.
Upcoming Improvements:
โข Expand reasoning to all behaviors beyond destination handling.
โข Add pothole avoidance.
โข Improve driver monitoring system sensitivity with better eye gaze tracking, eye wear handling, and higher accuracy in variable lighting conditions.
New release of FSD Supervised now starting to roll out
This update brings 20% faster reaction time to further increase safety, among many other improvements
Full release notes below
Full Self-Driving (Supervised) v14.3 includes
- Upgraded the Reinforcement Learning (RL) stage of training the FSD neural network, resulting in improvements in a wide variety of driving scenarios.
- Upgraded the neural network vision encoder, improving understanding in rare and low-visibility scenarios, strengthening 3D geometry understanding, and expanding traffic sign understanding.
- Rewrote the AI compiler and runtime from the ground up with MLIR, resulting in 20% faster reaction time and improving model iteration speed.
- Mitigated unnecessary lane biasing and minor tailgating behaviors.
- Increased decisiveness of parking spot selection and maneuvering.
- Improved parking location pin prediction, now shown on a map with a (P) icon.
- Enhanced response to emergency vehicles, school buses, right-of-way violators, and other rare vehicles.
- Improved handling of small animals by focusing RL training on harder examples and adding rewards for better proactive safety.
- Improved traffic light handling at complex intersections with compound lights, curved roads, and yellow light stopping โ driven by training on hard RL examples sourced from the Tesla fleet.
- Improved handling for rare and unusual objects extending, hanging, or leaning into the vehicle path by sourcing infrequent events from the fleet.
- Improved handling of temporary system degradations by maintaining control and automatically recovering without driver intervention, reducing unnecessary disengagements.
Upcoming Improvements
- Expand reasoning to all behaviors beyond destination handling.
- Add pothole avoidance.
- Improve driver monitoring system sensitivity with better eye gaze tracking, eye wear handling, and higher accuracy in variable lighting conditions.