BROADCASTS.com

\u27a4 One of Tesla\u2019s largest shareholders advocates for stock buyback, should Tesla do it?
\u27a4 FSD Beta 10.12 release notes leak
\u27a4 Wedbush reduces TSLA price target
\u27a4 California mayor discloses massive Supercharging site
\u27a4 NHTSA investigates Tesla crash in a California
\u27a4 Twitter execs discuss possible acquisition
\u27a4 Bill Gates declines to comment on Tesla again

Twitter: https://www.twitter.com/teslapodcast
Patreon: https://www.patreon.com/tesladailypodcast
Tesla Referral: https://ts.la/robert47283

FSD 10.12 Release Notes:

\u2022 Upgraded decision making framework for unprotected left turns with better modeling of objects' response to ego's actions by adding more features that shape the go/no-go decision. This increases robustness to noisy measurements while being more sticky to decisions within a safety margin. The framework also leverages median safe regions when necessary to maneuver across large turns and accelerating harder through maneuvers when required to safely exit the intersection.
\u2022 Improved creeping for visibility using more accurate lane geometry and higher resolution occlusion detection.
\u2022 Reduced instances of attempting uncomfortable turns through better integration with object future predictions during lane selection.
\u2022 Upgraded planner to rely less on lanes to enable maneuvering smoothly out of restricted space.
\u2022 Increased safety of turns with crossing traffic by improving the architecture of the lanes neural network which greatly boosted recall and geometric accuracy of crossing lanes.
\u2022 Improved the recall and geometric accuracy of all lane predictions by adding 180k video clips to the training set.
\u2022 Reduced traffic control related false slowdowns through better integration with lane structure and improved behavior with respect to yellow lights.
\u2022 Improved the geometric accuracy of road edge and line predictions by adding a mixing/coupling layer with the generalized static obstacle network.
\u2022 Improved geometric accuracy and understanding of visibility by retraining the generalized static obstacle network with improved data from the autolabeler and by adding 30k more videos clips.
\u2022 Improved recall of motorcycles, reduced velocity error of close-by pedestrians and bicyclists, and reduced heading error of pedestrians by adding new sim and autolabeled data to the training set.
\u2022 Improved precision of the "is parked" attribute on vehicles by adding 41k clips to the training set. Solved 48% of failure cases captured by our telemetry of 10.11.
\u2022 Improved detection recall of far-away crossing objects by regenerating the dataset with improved versions of the neural networks used in the autolabeler which increased data quality.
\u2022 Improved offsetting behavior when maneuvering around cars with open doors.
\u2022 Improved angular velocity and lane-centric velocity for non-VRU objects by upgrading it into network predicted tasks.
\u2022 Improved comfort when lane changing behind vehicles with harsh deceleration by tighter integration between lead vehicles future motion estimate and planned lane change profile.
\u2022 Increased reliance on network-predicted acceleration for all moving objects, previously only longitudinally relevant objects.
\u2022 Updated nearby vehicle assets with visualization indicating when a vehicle has a door open.
\u2022 Improved system frame rate +1.8 frames per second by removing three legacy neural networks.

Executive producer Jeremy Cooke
Executive producer Troy Cherasaro
Executive producer Andre/Maria Kent
Executive producer Jessie Chimni
Executive producer Michael Pastrone
Executive producer Richard Del Maestro
Executive producer John Beans
Music by Evan Schaeffer

Disclosure: Rob Maurer is long TSLA stock & derivatives