Tesla deploys FSD (Supervised) v13.2.2.1 following a recent release

Tesla has released Full Self Driving (FSD) Supervised v13.2.2.1 to HW4 (AI4) vehicles, this new update comes a few days after rolling FSD v13.2.2. Similar to the previous version, this update package also includes holiday update features.

The update content is similar to the previous release and may include some new optimizations but it’s part of the wider rollout.

Here’s what you will see in the changelog.

Tesla FSD v13.2.2.1 (Credit – Tesla)

Includes:

• 36 Hz, full-resolution Al4 video inputs
• Native Al4 inputs and neural network architectures
• 4.2x data scaling
• 5x training compute scaling (enabled by the Cortex cluster)
• Reduced photon-to-control latency by 2x
• Speed Profiles on both City Streets and Highways
• Integrated unpark, reverse, and park capabilities
• Improved reward predictions for collision avoidance
• Improved camera cleaning
• Redesigned controller for smoother, more accurate tracking
• Dynamic routing around road closures, which displays them along an affected route when they are detected by the fleet

Upcoming Improvements:

• 3x model size scaling
• 3x model context length scaling
• Integrated unpark, reverse, and park capabilities
• Audio inputs for better handling of emergency vehicles
• Improved reward predictions for navigation
• Improvements to false braking and slower driving in parking lots
• Redesigned controller for smoother, more accurate tracking
• Support for destination options including pulling over, parking in a spot, driveway, or garage
• Efficient representation of maps and navigation inputs
• Improved camera cleaning and handling of camera occlusions