Tesla FSD 14.3 Launches with 2026.2.9.6 Update: Release Notes

Tesla has officially started rolling out Full Self-Driving (Supervised) v14.3 with software version 2026.2.9.6. This update is being hailed as the final piece of the puzzle for Tesla’s autonomy goals, primarily due to the foundational rewrite of its AI architecture.

By rebuilding the AI compiler and runtime from the ground up using MLIR, Tesla has achieved a 20% faster reaction time. This speed is critical for real-world safety, allowing the vehicle to process complex environments and react to hazards faster than a human driver. Combined with a new vision encoder that masters 3D geometry, the car now understands the world with unprecedented depth and clarity, even in low-visibility conditions.

The first folks to get FSD 14.3 appear to be prominent Tesla influencers such as Sawyer Merritt, DirtyTesla, Chuck Cook and more.

Full Self-Driving (Supervised) v14.3 includes (via Sawyer Merritt):

• 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 – 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.

Let’s stay tuned for first-drive videos of FSD 14.3. This is super exciting for those with HW4 vehicles and also signals that FSD 14 lite should hopefully be in the works for those with HW3 hardware.