With FSD V13.2.6 continuing to make its way to AI4 vehicles, Tesla has been on a streak with minor FSD improvements since the launch of FSD V13 just a little over two months ago.
FSD V13 brought a new slate of features, including Start FSD from Park, Reverse, and Park at Destination. It also introduced full-resolution video input using the AI4 cameras at 36hz and made use of the new Cortex supercomputer to get faster and more accurate decision-making.
So, what’s next with FSD V14? Tesla gave us a sneak peek at what’s next for FSD.
FSD V14
The standout feature of FSD V14 will be auto-regressive transformers. While that’s a complex term for those unfamiliar with AI or machine learning, we’ll break it down.
Auto-Regressive
An auto-regressive transformer processes sequential data in time, using that information to predict future elements based on previous ones. Imagine completing a sentence: You use the words already written to guess what comes next. This process isn't just about filling in the blank; it's about understanding the flow of the sentence and anticipating the speaker's intent.
FSD could analyze a sequence of camera images to identify pedestrians and predict their likely path based on their current movement and surrounding context. The system's auto-regressive nature allows it to learn from past sequences and improve its predictions over time, adapting to different driving scenarios.
Today, FSD reacts to what it sees, but soon it’ll be able to anticipate what will help, much like humans.
Transformers
The second part of that term is transformer, which is a component used to understand the relationships of elements inside a time sequence. It identifies which parts of the input are most crucial for making accurate predictions, allowing the system to prioritize information much like a human would. Think of it as weighing different pieces of evidence to arrive at a conclusion. For example, a transformer might recognize that a blinking turn signal is more important than the color of the car when predicting a lane change.
Putting It Together
Putting all that together, Tesla’s use of auto-regressive transformers means they’ll be working on how FSD can predict the plans and paths of the world around it. This will improve FSD’s already powerful perception and allow it to predict how other vehicles and vulnerable road users (VRUs) will behave.
What it all comes down to is that FSD will be able to make better decisions and plan its paths by making more informed, human-like decisions. That will be a big step towards improving V13 - which already has some very effective decision-making.
Larger Model and Context Size
Ashok Elluswamy (Tesla’s VP of AI) stated that FSD V14 will see larger model and context sizes in FSD V14, which coincidentally are listed in the upcoming improvements section of FSD V13.2.6. If we compare what Ashok said to what’s listed in the upcoming features section, the model and context sizes should grow by 3x.
Interestingly, Ashok says that AI4’s memory limits context size. Context is essentially the history of what the vehicle remembers, which is used for future decisions. Since this information is stored in memory, it’ll always be limited by memory, but it’s worth noting that Ashok mentioned that Tesla is restricted by the memory in the AI4 computer.
Leverage Audio Input
Tesla is already gathering audio data in existing FSD versions so that it can start training models with audio as well, truly making FSD more human-like. According to Ashok, FSD V14 will be the first version to take advantage of audio input for FSD driving. This will primarily be used for detecting emergency vehicles, but we can see this expanding to other sounds that help humans adjust their driving, such as car crashes, loud noises, honking, etc. At the very least, FSD could be more cautious when hearing a noise that matches an accident or vehicle honking.
FSD V14 Release Date
We haven’t heard from Elon Musk or Ashok Elluswamy about when FSD V14 will arrive. Ashok previously stated that FSD V13.4 would see audio inputs being used, but at Tesla’s earnings call, Tesla said that audio input would become relevant in V14, making it seem like Tesla may scrap V13.4 for V14.
Since Tesla is planning to launch their Robotaxi network in Texas this June, which is just four months away, FSD V14 may be the version used for its autonomous taxi fleet.
Subscribe
Subscribe to our newsletter to stay up to date on the latest Tesla news, upcoming features and software updates.
With Tesla’s first major expansion of the Robotaxi Geofence now complete and operational, they’ve been hard at work with validation in new locations - and some are quite the drive from the current Austin Geofence.
Validation fleet vehicles have been spotted operating in a wider perimeter around the city, from rural roads in the west end to the more complex area closer to the airport. Tesla mentioned during their earnings call that the Robotaxi has already completed 7,000 miles in Austin, and it will expand its area of operation to roughly 10 times what it is now. This lines up with the validation vehicles we’ve been tracking around Austin.
Based on the spread of the new sightings, the potential next geofence could cover a staggering 450 square miles - a tenfold increase from the current service area of roughly 42 square miles. You can check this out in our map below with the sightings we’re tracking.
If Tesla decides to expand into these new areas, it would represent a tenfold increase over their current geofence, matching Tesla’s statement. The new area would cover approximately 10% of the 4,500-square-mile Austin metropolitan area. If Tesla can offer Robotaxi services in that entire area, it would prove they can tackle just about any city in the United States.
From Urban Core to Rural Roads
The locations of the validation vehicles show a clear intent to move beyond the initial urban and suburban core and prepare the Robotaxi service for a much wider range of uses.
In the west, validation fleet vehicles have been spotted as far as Marble Falls - a much more rural environment that features different road types, higher speed limits, and potentially different challenges.
In the south, Tesla has been expanding towards Kyle, which is part of the growing Austin-San Antonio suburban corridor spanning Highway 35. San Antonio is only 80 miles (roughly a 90-minute drive) away, and could easily become part of the existing Robotaxi area if Tesla obtains regulatory approval there.
In the East, we haven’t spotted any new validation vehicles. This is likely because Tesla’s validation vehicles originate from Giga Texas, which is located East of Austin. We won’t really know if Tesla is expanding in this direction until they start pushing past Giga Texas and toward Houston.
Finally, there have been some validation vehicles spotted just North of the new expanded boundaries, meaning that Tesla isn’t done in that direction either. This direction consists of the largest suburban areas of Austin, which have so far not been serviced by any form of autonomous vehicle.
Rapid Scaling
This new, widespread validation effort confirms what we already know. Tesla is pushing for an intensive period of public data gathering and system testing in a new area, right before conducting geofence expansions. The sheer scale of this new validation zone tells us that Tesla isn’t taking this slowly - the next step is going to be a great leap instead, and they essentially confirmed this during this Q&A session on the recent call. The goal is clearly to bring the entire Austin Metropolitan area into the Robotaxi Network.
While the previous expansion showed off just how Tesla can scale the network, this new phase of validation testing is a demonstration of just how fast they can validate and expand their network. The move to validate across rural, suburban, and urban areas simultaneously shows their confidence in these new Robotaxi FSD builds.
Eventually, all these improvements from Robotaxi will make their way to customer FSD builds sometime in Q3 2025, so there is a lot to look forward to.
For years, the progress of Tesla’s FSD has been measured by smoother turns, better lane centering, and more confident unprotected left turns. But as the system matures, a new, more subtle form of intelligence is emerging - one that shifts its attention to the human nuances of navigating roads. A new video posted to X shows the most recent FSD build, V13.2.9, demonstrating this in a remarkable real-world scenario.
Toll Booth Magic
In the video, a Model Y running FSD pulls up to a toll booth and smoothly comes to a stop, allowing the driver to handle payment. The car waits patiently as the driver interacts with the attendant. Then, at the precise moment the toll booth operator finishes the transaction and says “Have a great day”, the vehicle starts moving, proceeding through the booth - all without any input from the driver.
If you notice, there’s no gate here at this toll booth. This interaction all happened naturally with FSD.
While the timing was perfect, the FSD wasn’t listening to the conversation for clues (maybe one day, with Grok?) The reality, as explained by Ashok Elluswamy, Tesla’s VP of AI, is even more impressive.
It can see the transaction happening using the repeater & pillar cameras. Hence FSD proceeds on its own when the transaction is complete 😎
FSD is simply using the cameras on the side of the vehicle to watch the exchange between the driver and attendant. The neural network has been trained on enough data that it can visually recognize the conclusion of a transaction - the exchange of money or a card and the hands pulling away - and understands that this is the trigger to proceed.
The Bigger Picture
This capability is far more significant than just a simple party trick. FSD is gaining the ability to perceive and navigate a world built for humans in the most human-like fashion possible.
If FSD can learn what a completed toll transaction looks like, it’s an example of the countless other complex scenarios it’ll be able to handle in the future. This same visual understanding could be applied to navigating a fast-food drive-thru, interacting with a parking garage attendant, passing through a security checkpoint, or boarding a ferry or vehicle train — all things we thought that would come much later.
These human-focused interactions will eventually become even more useful, as FSD becomes ever more confident in responding to humans on the road, like when a police officer tells a vehicle to go a certain direction, or a construction worker flags you through a site. These are real-world events that happen every day, and it isn’t surprising to see FSD picking up on the subtleties and nuances of human interaction.
This isn’t a pre-programmed feature for a specific toll booth. It is an emergent capability of the end-to-end AI neural nets. By learning from millions of videos across billions of miles, FSD is beginning to build a true contextual understanding of the world. The best part - with a 10x context increase on its way, this understanding will grow rapidly and become far more powerful.
These small, subtle moments of intelligence are the necessary steps to a truly robust autonomous system that can handle the messy, unpredictable nature of human society.
