The release notes for Tesla FSD Beta V11.3 have been shared online. Observers from the electric vehicle community suggest that Tesla Full Self-Driving Beta 11.3 is rolling out to the company’s employee FSD Beta testers, at least for now.
The following are Tesla’s FSD Beta V11.3 release notes:
- Enabled FSD Beta on highway. This unifies the vision and planning stack on and off-highway and replaces the legacy highway stack, which is over four years old. The legacy highway stack still relies on several single-camera and single-frame networks, and was setup to handle simple lane-specific maneuvers. FSD Beta’s multi-camera video networks and next-gen planner, that allows for more complex agent interactions with less reliance on lanes, make way for adding more intelligent behaviors, smoother control and better decision making.
- Added voice drive-notes. After an intervention, you can now send Tesla an anonymous voice message describing your experience to help improve Autopilot.
- Expanded Automatic Emergency Braking (AEB) to handle vehicles that cross ego’s path. This includes cases where other vehicles run their red light or turn across ego’s path, stealing the right-of-way.
- Replay of previous collisions of this type suggests that 49% of the events would be mitigated by the new behavior. This improvement is now active in both manual driving and autopilot operation.
- Improved autopilot reaction time to red light runners and stop sign runners by 500ms, by increased reliance on object’s instantaneous kinematics along with trajectory estimates.
- Added a long-range highway lanes network to enable earlier response to blocked lanes and high curvature.
- Reduced goal pose prediction error for candidate trajectory neural network by 40% and reduced runtime by 3X. This was achieved by improving the dataset using heavier and more robust offline optimization, increasing the size of this improved dataset by 4X, and implementing a better architecture and feature space.
- Improved occupancy network detections by oversampling on 180K challenging videos including rain reflections, road debris, and high curvature.
- Improved recall for close-by cut-in cases by 20% by adding 40k autolabeled fleet clips of this scenario to the dataset. Also improved handling of cut-in cases by improved modeling of their motion into ego’s lane, leveraging the same for smoother lateral and longitudinal control for cut-in objects.
- Added “lane guidance module and perceptual loss to the Road Edges and Lines network, improving the absolute recall of lines by 6% and the absolute recall of road edges by 7%.
- Improved overall geometry and stability of lane predictions by updating the “lane guidance” module representation with information relevant to predicting crossing and oncoming lanes.
- Improved handling through high speed and high curvature scenarios by offsetting towards inner lane lines.
- Improved lane changes, including: earlier detection and handling for simultaneous lane changes, better gap selection when approaching deadlines, better integration between speed-based and nav-based lane change decisions and more differentiation between the FSD driving profiles with respect to speed lane changes.
- Improved longitudinal control response smoothness when following lead vehicles by better modeling the possible effect of lead vehicles’ brake lights on their future speed profiles.
- Improved detection of rare objects by 18% and reduced the depth error to large trucks by 9%, primarily from migrating to more densely supervised autolabeled datasets.
- Improved semantic detections for school busses by 12% and vehicles transitioning from stationary-to-driving by 15%. This was achieved by improving dataset label accuracy and increasing dataset size by 5%.
- Improved decision making at crosswalks by leveraging neural network based ego trajectory estimation in place of approximated kinematic models.
- Improved reliability and smoothness of merge control, by deprecating legacy merge region tasks in favor of merge topologies derived from vector lanes.
- Unlocked longer fleet telemetry clips (by up to 26%) by balancing compressed IPC buffers and optimized write scheduling across twin SOCs.
Here are the V11.3 release notes again if you haven't seen them. Very happy to see improvements in rain reflections as that was rare, but could give some insane errors #FSDBeta @elonmusk pic.twitter.com/ZIOcIhmUMd
— Dirty Tesla (@DirtyTesLa) February 20, 2023
Several longtime FSD Beta testers have pointed out some key improvements that would likely be very appreciated by users in V11.3. These include the systems’ improved handling through high speed and high curvature scenarios, as well as improvements to Automatic Emergency Braking (AEB). With the improvements in place, FSD Beta V11.3 would behave closer to a proper human driver.
Comments from longtime Tesla FSD Beta testers also suggest that V11.3 is still only being released for company employees for now. Considering Tesla’s past updates, it would not be surprising if the greater FSD Beta fleet gets the V11.3 update in the coming week or so. This is, of course, unless V11.3 ends up going the way of FSD Beta V11, which was released to employees in November but not to the greater fleet of FSD Beta testers.
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 says Tesla will take Safety Drivers out of Robotaxi: here’s when
“The safety driver is just there for the first few months to be extra safe. Should be no safety driver by end of year.”
Tesla CEO Elon Musk said today that the company plans to completely eliminate Safety Drivers from its Robotaxi fleet, which differs from the Safety Monitors it uses.
Tesla’s Robotaxi platform utilizes employees in the front passenger seat during city rides in Austin and the driver’s seat of the vehicles during highway operations in Austin, as well as during all rides in the Bay Area.
Tesla adjusts Robotaxi safety monitor strategy in Austin with new service area
Musk said the presence of a Safety Driver “is just there for the first few months to be extra safe,” but there are plans to remove them in an effort to remove the crutches the company uses during the early stages of Robotaxi.
The CEO then outlined a timeframe for when it would remove the presence of an employee in the driver’s seat in both Austin and the Bay Area. He said there “should be no safety driver by end of year.”
The safety driver is just there for the first few months to be extra safe.
Should be no safety driver by end of year.
— Elon Musk (@elonmusk) September 4, 2025
Having a Safety Driver or Monitor has been a major point of criticism from Robotaxi skeptics and Tesla critics.
However, Tesla has maintained that its priority in the early stages is the safety of riders, which will keep things running; even a single negative incident could derail self-driving efforts as a whole, including those outside of the company.
Tesla executives have said their attitude toward safety is “paranoid,” but for good reason: an accident could set back the progress that it and many other companies, including rivals like Waymo, have made in the past few years.
For now, it might be a point of criticism for some, but it’s smart in the near term. Musk plans for Tesla to have Robotaxi operating for half of the U.S. population by the end of the year as well, so it will be interesting to see if it can maintain these timelines.
News
Tesla is already giving Robotaxi privileges hours after opening public app
This morning, Tesla launched the app in the Apple Store, giving iOS users the ability to download and join a waitlist in hopes of gaining access.
Tesla is already giving Robotaxi privileges to those who downloaded the app and joined its waitlist just hours after it launched in the United States.
As the Robotaxi platform has been operating in Austin for several months, Tesla is now allowing the general public to download its app and call for a driverless ride in the city.
Tesla Robotaxi makes major expansion with official public app launch
The company previously sent invitations to select media outlets and Tesla influencers, seeking initial feedback on the performance of the Robotaxi platform.
There have been positive reviews, but, as with any Beta program, some mishaps have also occurred, although none have been significant.
As of the writing of this article, the City of Austin only lists one incident involving a Tesla Robotaxi, noting it as a “Safety Concern,” but not an accident or collision.
This morning, Tesla launched the app in the Apple Store, giving iOS users the ability to download and join a waitlist in hopes of gaining access.
Tesla is already granting Robotaxi access to several of those who have downloaded the app and gotten on the waitlist early:
Been getting a lot of messages from people who downloaded Tesla’s new Robtoaxi app last night and already have access to the company’s robotaxi and ride-hailing services. pic.twitter.com/xgbki1D3Lw
— Sawyer Merritt (@SawyerMerritt) September 4, 2025
With the launch of the public app, we were not too sure how soon Tesla would be able to initiate bringing more riders into the Robotaxi program. The immediate admittance for some riders just hours after the launch is a big positive and is surely a sign of strength for Tesla and its Robotaxi program.
What many will look for moving forward is the expansion of the geofence, which does not seem like a problem, as Tesla has already managed to do this on three occasions. The most recent expansion has expanded the service area to approximately 190 square miles.
People will also look for evidence of fleet expansion, a concern that has been a concern for many, especially since Tesla has not been completely transparent about it. They have revealed a recent service fleet growth of 50 percent, but there has been no specific number of vehicles mentioned.
News
Tesla explains why Robotaxis now have safety monitors in the driver’s seat
The update to Austin’s safety monitors became a point of interest among Tesla watchers on social media.
Tesla has provided an explanation about the presence of safety monitors in the driver’s seat of its autonomous Robotaxi units.
The autonomous ride-hailing service is currently being deployed in Austin and the Bay Area, with more cities across the United States expected to gain access to the service later this year.
Safety Monitors
When Tesla launched its initial Robotaxi program in Austin, the company made headlines for operating vehicles without a human in the driver’s seat. Even with this setup, however, Tesla still had safety monitors in the passenger seat of the Robotaxis. The safety monitors, which do not interact with passengers, have been observed to report issues and other behaviors from the autonomous vehicles in real time.
Safety monitors on the driver’s seat were also employed in the service’s Bay Area rollout, though numerous members of the EV community speculated that this was likely done to meet regulations in California. However, with the expansion of the Austin geofence, riders in Tesla’s Robotaxis observed that the safety monitors in the city have been moved to the driver’s seat as well.
Tesla’s explanation
The update to Austin’s safety monitors became a point of interest among Tesla watchers on social media. Longtime FSD tester Whole Mars Catalog, for one, speculated that the move might be due to Texas’ new regulations for autonomous vehicles, which took effect recently. Interestingly enough, the official Tesla Robotaxi account on X responded to the FSD tester, providing an explanation behind the safety monitor’s move to the driver’s seat.
“Safety monitors are only in the driver’s seat for trips that involve highway driving, as a self-imposed cautious first step toward expanding to highways,” the Tesla Robotaxi account noted.
Tesla has been extremely cautious with its autonomous driving program, particularly with the rollout of its Robotaxi service, which use Unsupervised FSD. This is quite understandable considering the negative media slant that Tesla is consistently subjected to, which could very well result in minute incidents or mistakes by Robotaxis being blown out of proportion.
Elon Musk says Tesla will take Safety Drivers out of Robotaxi: here’s when
Tesla is already giving Robotaxi privileges hours after opening public app
Tesla explains why Robotaxis now have safety monitors in the driver’s seat
-
News5 days agoTesla is overhauling its Full Self-Driving subscription for easier access
-
Elon Musk6 days agoElon Musk shares unbelievable Starship Flight 10 landing feat
-
Elon Musk1 week agoElon Musk reveals when SpaceX will perform first-ever Starship catch
-
Elon Musk1 week agoSpaceX Starship Flight 10 was so successful, it’s breaking the anti-Musk narrative
-
News3 days agoTesla appears to be mulling a Cyber SUV design
-
Elon Musk1 day agoTesla’s next-gen Optimus prototype with Grok revealed
-
News6 days agoTesla expands crazy new lease deal for insane savings on used inventory
-
News6 days agoTesla talks Semi ramp, Optimus, Robotaxi rollout, FSD with Wall Street firm