News
Tesla FSD Beta 10.69 release notes highlight better left turns, smoother driving
Tesla released FSD Beta 10.69 to the first round of testers over the weekend. Read v.10.69’s release notes below to check out the latest improvements.
Stay in your Lanes
- Added a new “deep lane guidance” module to the Vector Lanes neural network which fuses features extracted from the video streams with coarse map data, i.e. lane counts and lane connectivites. This architecture achieves a 44% lower error rate on lane topology compared to the previous model, enabling smoother control before lanes and their connectivities becomes visually apparent. This provides a way to make every Autopilot drive as good as someone driving their own commute, yet in a sufficiently general way that adapts for road changes.
Nothing Like Smooth Driving
- Improved overall driving smoothness, without sacrificing latency, through better modeling of system and actuation latency in trajectory planning. Trajectory planner now independently accounts for latency from steering commands to actual steering actuation, as well as acceleration and brake commands to actuation. This results in a trajectory that is a more accurate model of how the vehicle would drive. This allows better downstream controller tracking and smoothness while also allowing a more accurate response during harsh manevuers.
- Increased smoothness for protected right turns by improving the association of traffic lights with slip lanes vs yield signs with slip lanes. This reduces false slowdowns when there are no relevant objects present and also improves yielding position when they are present.
- Reduced false slowdowns near crosswalks. This was done with improved understanding of pedestrian and bicyclist intent based on their motion.
- Enabled creeping for visibility at any intersection where objects might cross ego’s path, regardless of presence of traffic controls.
- Improved accuracy of stopping position in critical scenarios with crossing objects, by allowing dynamic resolution in trajectory optimization to focus more on areas where finer control is essential.
- Reduced latency when starting from a stop by accounting for lead vehicle jerk.
Chuck’s Left Turn
- Improved unprotected left turns with more appropriate speed profile when approaching and exiting median crossover regions, in the presence of high speed cross traffic (“Chuck Cook style” unprotected left turns). This was done by allowing optimizable initial jerk, to mimic the harsh pedal press by a human, when required to go in front of high speed objects. Also improved lateral profile approaching such safety regions to allow for better pose that aligns well for exiting the region. Finally, improved interaction with objects that are entering or waiting inside the median crossover region with better modeling of their future intent.
Safety is Number 1
- Added control for arbitrary low-speed moving volumes from Occupancy Network. This also enables finer control for more precise object shapes that cannot be easily represented by a cuboid primitive. This required predicting velocity at every 3D voxel. We may now control for slow-moving UFOs.
- Made speed profile more comfortable when creeping for visibility, to allow for smoother stops when protecting for potentially occluded objects.
- Improved speed when entering highway by better handling of upcoming map speed changes, which increases the confidence of merging onto the highway.
- Enabled faster identification of red light runners by evaluating their current kinematic state against their expected braking profile.
Tesla FSD “Brain” Improvements
- Upgraded Occupancy Network to use video instead of images from single time step. This temporal context allows the network to be robust to temporary occlusions and enables prediction of occupancy flow. Also, improved ground truth with semantics-driven outlier rejection, hard example mining, and increasing the dataset size by 2.4x.
- Upgraded to a new two-stage architecture to produce object kinematics (e.g. velocity, acceleration, yaw rate) where network compute is allocated O(objects) instead of O(space). This improved velocity estimates for far away crossing vehicles by 20%, while using one tenth of the compute.
- Improved geometry error of ego-relevant lanes by 34% and crossing lanes by 21% with a full Vector Lanes neural network update. Information bottlenecks in the network architecture were eliminated by increasing the size of the per-camera feature extractors, video modules, internals of the autoregressive decoder, and by adding a hard attention mechanism which greatly improved the fine position of lanes.
- Improved recall of animals by 34% by doubling the size of the auto-labeled training set.
- Increased recall of forking lanes by 36% by having topological tokens participate in the attention operations of the autoregressive decoder and by increasing the loss applied to fork tokens during training.
- Improved velocity error for pedestrians and bicyclists by 17%, especially when ego is making a turn, by improving the onboard trajectory estimation used as input to the neural network.
- Improved recall of object detection, eliminating 26% of missing detections for far away crossing vehicles by tuning the loss function used during training and improving label quality.
- Improved object future path prediction in scenarios with high yaw rate by incorporating yaw rate and lateral motion into the likelihood estimation. This helps with objects turning into or away from ego’s lane, especially in intersections or cut-in scenarios.
Tesla is rolling out FSD Beta v.10.69 in phases, starting with ~1,000 testers over the weekend. Once the update is rolled out for wide release, the price of FSD Beta will increase.
The Teslarati team would appreciate hearing from you. If you have any tips, contact me at maria@teslarati.com or via Twitter @Writer_01001101.
Elon Musk
Elon Musk reveals date of Tesla Full Self-Driving’s next massive release
Initially planned for a January or February release, v14.3 aims to add some reasoning and logic to the decisions that Full Self-Driving makes, which could improve a lot of things, including Navigation, which is a major complaint of many owners currently.
Tesla CEO Elon Musk revealed the date of Full Self-Driving’s next massive release: v14.3.
For months, Tesla owners with Hardware 4 have been utilizing Full Self-Driving v14.2 and subsequent releases. Currently, the most up-to-date FSD version is v14.2.2.5, which has definitely brought out mixed reviews. With releases, some things get better, and other things might regress slightly.
For the most part, things are better in terms of overall behavior.
However, many owners have been looking forward to the next release, which is v14.3, about which Musk has said many great things. Back in November, Musk said that v14.3 “is where the last big piece of the puzzle lands.”
He added:
“We’re gonna add a lot of reasoning and RL (reinforcement learning). To get to serious scale, Tesla will probably need to build a giant chip fab. To have a few hundred gigawatts of AI chips per year, I don’t see that capability coming online fast enough, so we will probably have to build a fab.”
Initially planned for a January or February release, v14.3 aims to add some reasoning and logic to the decisions that Full Self-Driving makes, which could improve a lot of things, including Navigation, which is a major complaint of many owners currently.
Tesla Full Self-Driving v14.2 is a considerable improvement from early versions of the suite, but we have written about the somewhat confusing updates that have come with recent versions.
Tesla Full Self-Driving v14.2.2.5 might be the most confusing release ever
They’ve been incredibly difficult to gauge in terms of progress because some things have gotten better, but there seems to be some real regression on a handful of things, especially with confidence and assertiveness.
Musk confirmed today on X that Tesla is already testing v14.3 internally right now. It will hit a wide release “in a few weeks,” so we should probably expect it by late April.
It’s in testing right now. Wide release in a few weeks.
— Elon Musk (@elonmusk) March 19, 2026
Overall, there are high hopes that v14.3 could be a true game changer for Tesla Full Self-Driving, as many believe it could be the version that Robotaxis in Austin, Texas, some of which are driverless and unsupervised, are running.
It could also include some major additions, including “Banish,” also referred to as “Reverse Summon,” which would go find a parking spot after dropping occupants off at their destination.
What Tesla will roll out, and when exactly it arrives, all remain to be seen, but fans have been ready for a new version as v14.2.2.5 has definitely run its course. We have had a lot of readers tell us their biggest request is to fix Navigation errors, which seem to be one of the most universal complaints among daily FSD users.
Cybertruck
Chattanooga Charge: Tesla and EV fans ready for the Southeast’s wildest Tesla party
From Cybertruck Convoys to Kid-Friendly Fun Zones: The Chattanooga Charge Has Something for Everyone
Hundreds of like-minded Tesla and EV enthusiasts are descending on Chattanooga Charge this weekend for the largest Tesla meet in the Southeast. Taking place on March 20–22, 2026 at the stunning Tennessee Riverpark.
If you were there last year, you’ll know that it’s the ultimate experience to see the wildest Teslas in action, see the best in EV tech, and arguably the most fun – finally put a name to the face and connect with those social media buddies IRL! Oh, and that epic night time Tesla light show is a once-in-a-lifetime experience that will transform the Riverpark into something out of a sci-fi film that’s remarkably unforgettable and must be seen in person.
This year’s event takes everything up a notch, with over 100 Cybertrucks expected to be on display, many sporting jaw-dropping modifications and custom wraps that push the boundaries of what these stainless steel beasts can look like.
Whether you’re a diehard Tesla fan, EV supporter, or just EV-mod-curious, the sheer spectacle is worth the drive.
The Chattanooga Charge doesn’t wait until Saturday morning to get started. The weekend technically kicks off Friday, March 20th, and the venue sets the tone immediately. Come share roadtrip stories over drinks at the W-XYZ Rooftop Bar on the top floor of the Aloft Chattanooga Hamilton Place Hotel, with sunset views over the city.
Come morning, nurse your hangover with a some good coffee, and convoy with hundreds of other Tesla and EV drivers through Chattanooga to the event for some morning meet and greets before the speaker panel starts and the food trucks fire up.
Tesla owner clubs travel from across the country to be here, not just to show off their vehicles,, but to connect, share, and celebrate a shared passion for the future of driving.
Sounds like a plan to me. See you there, guys. Don’t miss it. Get your tickets at ChattanoogaCharge.com and join the charge. 🔋⚡
Chattanooga Charge is a premier Tesla and EV gathering inspired by the X Takeover, known as one of the largest Tesla event gatherings. What began as a bold idea from the team at DIY Wraps/TESBROS, hosted in their hometown of Chattanooga, Tennessee, the event quickly became a movement across social media. The first annual Chattanooga Charge united over 16 Tesla clubs from 16 states, proof that the EV community was hungry for something big in the South. Year after year, the event has grown in scale, ambition, and heart.
News
Tesla Full Self-Driving gets latest bit of scrutiny from NHTSA
The analysis impacts roughly 3.2 million vehicles across the company’s entire lineup, and aims to identify how the suite’s degradation detection systems work and how effective they are when the cars encounter difficult visibility conditions.
The National Highway Traffic Safety Administration (NHTSA) has elevated its probe into Tesla’s Full Self-Driving (Supervised) suite to an Engineering Analysis.
The analysis impacts roughly 3.2 million vehicles across the company’s entire lineup, and aims to identify how the suite’s degradation detection systems work and how effective they are when the cars encounter difficult visibility conditions.
The step up into an Engineering Analysis is often required before the NHTSA will tell an automaker to issue a recall. However, this is not a guarantee that a recall will be issued.
🚨 The NHTSA said it was upgrading a probe into Tesla’s Full Self-Driving (Supervised) platform to an “engineering analysis”
It will examine 3.2 million vehicles and aims to determine its effectiveness in evaluating degraded road conditions pic.twitter.com/2dkrv1mR8o
— TESLARATI (@Teslarati) March 19, 2026
The NTHSA wants to examine Tesla FSD’s ability to assess road conditions that have reduced visibility, as well as detect degradation to alert the driver with sufficient time to respond.
The Office of Defects Investigation (ODI) will evaluate the performance of FSD in degraded roadway conditions and the updates or modifications Tesla makes to the degradation detection system, including the timing, purpose, and capabilities of the updates.
Tesla routinely ships software updates to improve the capabilities of the FSD suite, so it will be interesting to see if various versions of FSD are tested. Interestingly, you can find many examples from real-world users of FSD handling snow-covered roads, heavy rain, and single-lane backroads.
However, there are incidents that the NHTSA has used to determine the need for this probe, at least for now. The agency said:
“Available incident data raise concerns that Tesla’s degradation detection system, both as originally deployed and later updated, fails to detect and/or warn the driver appropriately under degraded visibility conditions such as glare and airborne obscurants. In the crashes that ODI has reviewed, the system did not detect common roadway conditions that impaired camera visibility and/or provide alerts when camera performance had deteriorated until immediately before the crash occurred.”
It continues to say in its report that a review of Tesla’s responses revealed additional crashes that occurred in similar environments showed FSD “did not detect a degraded state, and/or it did not present the driver with an alert with adequate time for the driver to react. In each of these crashes, FSD also lost track of or never detected a lead vehicle in its path.”
The next steps of the NHTSA Engineering Analysis require the agency to gather further information on Tesla’s attempts to upgrade the degradation detection system. It will also analyze six recent potentially related incidents.
The investigation is listed as EA26002.
Elon Musk reveals date of Tesla Full Self-Driving’s next massive release
Chattanooga Charge: Tesla and EV fans ready for the Southeast’s wildest Tesla party
