Last night Tesla finally launched FSD V13.2 with a bevy of new features for its early access testers with update 2024.39.10. While they barely missed Thanksgiving's floaty deadline, they still managed to deliver it in November, marking another big win for the Tesla AI team.
Early Access Only
FSD V13.2 started to roll out to early access testers - who generally get hands-on with the latest builds in advance of everyone else. They’re the equivalent of Tesla’s trusted testers who aren’t running internal builds - and they’re able to catch more scenarios outside of Tesla’s pretty extensive safety training suite.
If no major issues are spotted, Tesla will begin a slow rollout to more and more vehicles over the next few weeks. Assuming all goes well with this build, it could be in most customer’s hands by Christmas.
Of course, as a reminder, FSD V13 is still limited to vehicles equipped with AI4—and for now, anything but the Cybertruck. The Cybertruck is on its own FSD branch, without access to Actually Smart Summon and Speed Profiles, but with End to End on the Highway. The Cybertruck was recently upgraded to update 2024.39.5 (FSD V12.5.5.3).
FSD V13.2 Features
Let’s take a look at everything in FSD V13.2 - which is the build version going out now on Tesla software update 2024.39.10. While we previously got a short preview of what was expected with V13, we now can see everything included in FSD V13.2.
Start FSD from Park, Reverse & Park at Destination
Parked to Parked has been the goal for FSD for quite a while now. Elon Musk has been saying that it was going to be the key to demonstrating Tesla’s autonomy framework back with the release of V12.3.6 - when V12.5 was but a glimmer in the Tesla AI team’s eye.
Now, with V13, FSD has integrated three key functionalities.
Unpark: FSD can now be started while you’re still parked. Simply set your destination and tap and hold the new Start FSD button. The car will now shift out of park and into drive or reverse in order to get to its destination.
Reverse: FSD has finally gained the ability to shift. Not only can the vehicle go into reverse now, but it can seamlessly shift between Park, Drive and Reverse all by itself. It can be perform 3-point turns.
Park: When FSD reaches its destination, it will now park itself if it finds an open parking spot near the final location. Tesla says that further improvements are coming to this, and drivers will be able to pick between pulling over, parking in a parking spot, driveway or garage in the future.
If everything goes smoothly on a drive, users will no longer need to give the vehicle any input at all, from its original location to its final parking spot. No more user intervention other than supervision is needed, unless an intervention is needed.
I tried to get FSD 13.2 to park in my garage but it instead did a 3 point turn and tried to escape 😱 pic.twitter.com/EzEYcNvuuA
Until now, FSD V12.5 and V12.6 have been using reduced image quality at reduced framerates to match the lower resolution and lower refresh rate provided by Hardware 3 cameras. For the first time, FSD will be using AI4’s (previously known as Hardware 4) cameras at higher resolution and 36 frames per second.
In short, that means better image quality for both training and in use and higher accuracy for things like signage and distance measurement.
Speed Profiles for All Roads
FSD V12.5.6.2 brought new and improved Speed Profiles to both city streets and highways, including the new Hurry Mode, which replaced Assertive Mode. However, on V12.5.6.2, there were a few limitations - roads needed a fairly high minimum speed limit of 50mph (80km/h) or higher. Now, that’s no more. City Streets has speed profiles for all speed limits now.
Similar to the video resolution and refresh rate, AI4 has a lot of new hardware features that help optimize how fast FSD’s AI model can run. We dug into how Tesla’s Universal Translator streamlines FSD for each platform - this is a case of having fewer constraints and more optimization versus Hardware 3.
5x Training Compute
Cortex, Tesla’s massive new supercomputer cluster at Giga Texas, is now online and crunching data at a truly insane rate. It's one of the fastest AI clusters in the world—and it's dedicated to FSD. Tesla has 5x the training compute crunching away to solve the March of 9’s now that FSD is close to being feature complete.
Faster Decision Making
Tesla refactored how it handles image-to-processing in FSD V13 - another huge set of changes to improve performance. In this release - a 2x faster photon-to-control latency, which is massive. In layman’s terms - that’s faster decision-making - it was already faster than a human, and now it's twice as fast as it was before.
Insane product push on the week of my birthday.
We refactored the entire system to drastically simplify the pipeline — direct photons to control — yet providing a lot more functionality under the same unify framework.
One of the features Tesla lists in FSD V13.2 is the ability for the vehicle to collect and share audio snippets with Tesla. The vehicle will ask you whether you’re okay with sharing 10-second audio files with Tesla so that the vehicle can detect emergency vehicles by sound in the future.
Camera Visibility Detection
The vehicle will now prompt you at the end of a drive if visibility issues are detected. The new option is under Controls > Service > Camera Visibility. Tesla will also retain images from the cameras when the vehicle experiences visibility issues during a drive so that you can analyze them later.
One of the features V12.5 was supposed to bring was fleet-based dynamic routing. If a route was closed, your Tesla would turn around and navigate through an alternative path - and also warn the rest of the fleet of the closure.
V13 lets AI4 vehicles do this, and it's another element of the Robotaxi network that Tesla needs to get off the ground to ensure that once they do begin to deploy their first fleets - they function well. So far, with new job postings for Robotaxi Engineers and talks with Palo Alto to launch a Robotaxi service, things are on track for both Unsupervised FSD and Robotaxi sometime in 2025.
Better Traffic Controller
Another big update is a redesigned traffic controller - which makes for smoother and more accurate tracking of other vehicles and objects around the vehicle. We dug into how the traffic controller processes information in this article here, where you can learn all about how Tesla’s signal processing works.
Tesla has mentioned a lot of upcoming improvements panel for FSD V13 too, which includes bigger models, audio inputs, better navigation and routing, improvements to false braking, destination options, and better camera occlusion handling. That’s a pretty big list for V13, so we’ll keep an eye on all these upcoming features that are expected in a future release.
What About Hardware 3?
Tesla’s previous roadmap update didn’t mention HW3 getting FSD V13. Instead, those of us on Hardware 3 will need to keep waiting and looking for Tesla to optimize another FSD Model - until then, you’ll be on FSD V12.5.4.2, which is still a fairly capable build.
Tesla has mentioned that they could potentially upgrade HW3 computers - not cameras - if engineers aren’t able to get FSD Unsupervised working on HW3. While there isn’t a lot to share here yet, it certainly looks like HW3 owners will be receiving some sort of free hardware upgrade in the future, but it’s not clear yet when or what they will be.
Keep an eye out in the new year for updates on what’s coming next with HW3. We hope to see an optimized V13 build eventually make its way to HW3 sometime in the future - Tesla has been working pretty hard on this, so let’s give them some time.
Release Date
For everyone who’s been patiently waiting to see more of FSD V13 since the sneaky reveal at We, Robot, you’ll be waiting a bit longer. This build is currently going out to early access testers, who serve as a critical step in Tesla’s safety verification process.
Once Tesla is comfortable with the rate of disengagement, Tesla will evaluate their results, make any final changes, and then begin rolling it out in waves. Fingers crossed, wider waves for V13 will make their way to AI4 S3XY vehicles and the Cybertruck by Christmas.
Subscribe
Subscribe to our newsletter to stay up to date on the latest Tesla news, upcoming features and software updates.
Tesla vehicles rely heavily on external cameras for their advanced driver-assistance systems (ADAS) and the future of fully autonomous robotaxis. However, driving in bad weather presents a significant challenge: keeping those cameras clean. Without a reliable cleaning solution, Robotaxis, which depend entirely on vision, cannot function safely and effectively.
Tesla owner Chuck Cook recently brought up this issue on X, saying to the Tesla AI team, “While I agree cleaning cameras while supervised is definitely something we need to consider... having an official post from @Tesla_AI about cleaning our own cameras is a bit concerning. You have a plan for this, right? Unsupervised can’t have customers wiping cameras.”
The Tesla_AI team responded, “On a more serious note, a more comprehensive cleaning solution is being worked on.”
Front Cameras
With the redesigned 2025 Model Y, Tesla introduced a front-facing camera, joining the Cybertruck in this regard. The Model S and Model X are also slated to receive this upgrade in the future and we eventually expect all Tesla vehicles to come with one standard.
Camera Washers
While the addition of a front camera is a step forward, it introduces another yet camera that needs to be cleaned.
Currently, the Cybertruck is the only known Tesla model equipped with a dedicated camera washer. This system drips water onto the front camera lens, allowing the wind to blow the moisture away. While it’s a simple and effective feature, it’s unclear whether Tesla implemented a similar feature in the new Model Y.
Rear Camera Shield
Sawyer Merritt/X
Tesla recently added a small shield around the rear camera to reduce the amount of dirt and water splashing onto the lens. Additionally, the rear camera on the new Model Y was relocated from above the license plate to the trunk lid. This repositioning presumably helps keep the lens cleaner by reducing its exposure to road spray.
While these adjustments are helpful, they don’t fully solve the issue, especially in harsher environments with constant rain, snow, or road debris.
Potential Solutions
There are several possible ways Tesla could address this issue:
Camera Washers: Expanding the Cybertruck’s washer feature to all external cameras or at least to the rear camera could provide a straightforward solution for keeping lenses clean.
Lens Coatings: Applying special coatings that repel water, dirt, and debris could reduce buildup on camera lenses. However, these coatings would still have limitations in extreme weather conditions.
Software Alerts: Software already notifies drivers when a camera is obstructed or dirty, but this wouldn’t solve the issue without a hardware solution to physically clean the lens.
Given that the new Model Y has already been announced, it doesn’t sound like Tesla incorporated a “comprehensive” solution to the dirty camera issue.
Tesla’s Solution?
Tesla’s mention of working on a “comprehensive cleaning solution” raises questions about what’s in development. The new Model Y doesn’t appear to feature anything we’d classify as comprehensive, and it’s unclear whether it even has a front camera washer like the Cybertruck.
One potential solution could tie into Tesla’s Robotaxi plans. Tesla is building hubs for its Robotaxis, where vehicles can be cleaned and maintained using robotic systems. These cleaning hubs could include robotic arms that wipe down exterior cameras when needed.
While this approach may work for Robotaxis in most situations, it doesn’t address the needs of private Tesla owners who rely on their vehicles daily. Tesla may assume that individual owners can manually clean their cameras as needed.
2024 was an amazing year for Tesla. Tesla went from FSD 12.1 in early January to FSD V13.2 by the end of November. While FSD appeared to be stagnant for a while, FSD V13 revived Tesla’s potential for an autonomous future. It made a lot of us realize that Tesla may be closer to an unsupervised version than we initially thought. While there are still leaps to be made to truly be unsupervised, Tesla is now closer than ever and may be able to release a geofenced version later this year or next year.
2024 also brought a new UI in the Spring Update and many exciting features such as Actually Smart Summon, Apple Watch support, Weather radar, new music services, hands-free trunk opening and many more.
As 2025 kicks off, we’re tempted to look at what Tesla vehicles could look like by the end of the year. We’ll take a look at new vehicles, improved hardware and new software features.
FSD
Tesla FSD V13 has set the bar pretty high, but let’s focus on the features we want to see. Of course, right off the bat, we know that Unsupervised FSD is possible sometime in 2025. While we don’t expect to see it early, there is a good chance we could see it in the latter half of the year in specific cities.
Tesla has been working with both Palo Alto in California and Austin in Texas on establishing the first Tesla Robotaxi network, so when Tesla finally launches in a specific market, its likely to be in one of these two.
Hardware 3
While FSD 12.6.1 is rolling out to a variety of vehicles with hardware 3, it’s still not V13. It does include the new highway stack and improved smoothness, but it lacks other V13 features such as the ability to Park, Unpark, and Reverse - the key features that really makeup FSD V13. The “Tap to Start FSD” button is also not available for HW3 or the Cybertruck.
Cybertruck
While the Cybertruck is already running FSD V13, it still lacks a lot of the same features as HW3 vehicles. Actually Smart Summon is also not available on the Cybertruck - it never received it with the initial launch of ASS earlier this year. Cybertruck is already a sight to see on roads and in parking lots, and a self-driving Cybertruck with nobody in it? Alien technology right there.
Better ASS
Actually, Smart Summon was a huge leap forward for Tesla’s robotaxi ambitions, and it really signaled just how far they’ve come with autonomy. However, it's still quite limited, with a fairly short range in North America of just 215 feet (65m). Then again, anything is better than the current European launch, with a paltry range of just 19.5 feet (6m) in some European nations.
Longer Range, both in North America - but especially in Europe - will be one of the keys to making it a far more useful feature than it already is. Most parking lots are far larger than the 215-foot distance that Actually Smart Summon currently supports, so in order to use it as designed, you really need to be parked near where you want to summon.
Doubling that distance to 500 feet will make a big difference in being able to summon your car from a reasonable distance, but with that much of a leap, Tesla will also need to allow Actually Smart Summon to be able to function on public roads for short times. Given that NHTSA has now opened up an investigation for Actually Smart Summon, these changes will likely not occur until the software feature is improved.
FSD in Europe & China
Today, Full Self-driving is restricted to just the United States and Canada - so most of North America. In fact, Mexico is geo-fenced, and FSD gets completely disabled when a vehicle with it enabled drives across the border.
Putting aside Mexico, FSD is expected to make its way to Europe and China sometime in 2025, especially with changes to European regulations coming to help allow FSD to actually function in its Supervised format. We’ll probably see the launch of FSD to European markets in some fashion later this year, but expect it to be behind Tesla’s target date of Q1.
In China, Tesla recently began showing the option to enable FSD, but it's greyed out for now, indicating that it’s potentially close to launching. Tesla has received approval to start testing FSD in China, so at this point, it seems to be a matter of time - cutting through red tape and gathering enough initial training data are going to be key.
Right-hand drive markets are also an additional challenge, as Tesla previously mentioned. Training for the time being has been focused on Left Hand Drive markets, so RHD markets will require additional training and refinement for FSD to really shine there.
New Vehicle Launches
Tesla has been hinting at an upcoming event in their updated referral program, which includes a potential invite to a future Tesla event. While we just had the Robotaxi event and Tesla just showed off the Model Y Juniper refresh, there is still more to come.
Next-Gen Model - Project Redwood
Tesla’s next-gen model, internally known as Project Redwood, is getting close to launch. While many have referred to this as the Model 2 or Model Q, we’re still not sure what it’ll be called just yet - or even what it will really look like.
However, Tesla seems primed to launch the vehicle sometime this year, and it’ll be a fairly compact vehicle, 15% smaller and 30% lighter than the Model 3 - the same size as the average Mini. If Tesla manages to keep in line with its originally promised pricing targets of $25,000 USD, this will be one of the best-selling EVs available. We expect it to be heavily based off of the Cybercab, but time will tell.
Tesla Semi Factory
Ok, while this isn’t “launching” next year, the Giga Texas Semi Factory is expected to be completed and operational by the end of 2025, so we’re likely going to see the Tesla Semi fleet start getting ramped up and expanded in late 2025 and early 2026, and this is one of Tesla’s most exciting products.
It has the potential to make the biggest impact on carbon emissions and fuel usage in a consumer-adjacent industry, so we could see a lot of immediate positive change from Tesla’s Semi in day-to-day life.
We’re super excited to see the Semi Factory get off the ground and more Tesla Semis begin to make their way into the wild.
Tesla Software
There have been some great software improvements made this year, especially during the UI redesign in the Spring Update, but there’s always more we’d love to see.
AirPlay / Google Cast Support
Being able to cast from your iOS or Android device right to your Tesla display would be a fantastic addition. Imagine not having to worry about logging in, or whether a streaming service is available via the browser or app in your vehicle. Simply load it on your phone and cast it to your vehicle.
The iOS / Android ecosystem is just too big for Tesla to try to rebuild it in their vehicles, and even if they did or emulated Android apps, you’d still be stuck logging in to each service.
We all already have a much faster computer in our pockets that’s used daily. Lots of times it’s used in short spurts, so being able to quickly send a vehicle to your vehicle’s larger display would be ideal.
While the feature was dropped in newer Model S and Model X vehicles, there is still a chance Tesla could bring it back with improved support. After all, the AMD APU likely outperforms the Steam Deck - a portable PC gaming device that was released in 2022.
However, support for those features on Android, as well as an Android Wear App, hasn’t been mentioned yet. We’d love for Tesla to show Android users some support, especially as Android holds a 50% market share in the US and over 70% globally.
Group Text Support
Today, if you’re in a group chat using RCS or iMessage and use your Tesla messages app to respond, you’ll likely send a direct message to the first person in the group rather than the whole group. What’s even worse is you can’t tell the difference between a message that’s sent directly to you or to a group.
That’s annoying at best, and downright a hassle at worst if you’re driving for a long time and unable to use your phone. It would be a fantastic wish come true if Tesla brought full support for group texts.
Smart Voice Assistant
Tesla’s current system is a list of voice commands that, while useful, leaves a lot to be desired when compared to modern voice assistants such as Google Assistant and even Alexa. However, a smart voice assistant based on an LLM that uses xAI’s Grok could be coming soon. Elon previously confirmed that Grok would make its way into Tesla vehicles.
Avoid Highways Option
Users have been asking for an ‘Avoid Highways’ option forever, as it’s a standard option in navigation systems nowadays. While the Alternate Routes feature is helpful, it may not always provide a route that avoids the highway.
In June, Elon Musk confirmed that a “Avoid Highways” option would be added to Tesla navigation, and now we have the new route options in China. We’re fairly confident that it will eventually be available in Tesla vehicles, but the question is when?
Arrival State of Charge in App
While the vehicle received arrival state of charge with the holiday update, we’re still waiting on it being added to the app. Tesla has already made some phrasing changes and other UI improvements that allow the new feature to slide right now.
We expect this to be added in the next month or two, but for anyone that does any serious trip planning from the Tesla app, it can’t come soon enough.
Live Activities
Not a Tesla App
Apple’s Live Activities are auto-updating, persistent notifications that can provide real-time information about a certain task. Live Activities are useful for Uber, flight information or other critical tasks that can change often. In Tesla’s case, they can be used when Supercharging or using Sentry Mode. You’d quickly be able to see how much time is remaining your charging session or how many Sentry Mode events you’ve received.
Tesla Energy
Tesla’s energy wing has been quietly doing a lot of work behind the scenes, so let’s take a moment to appreciate everything that’s happening here.
These V4 Supercharger cabinets are capable of dispensing up to 500kW for the Cybertruck, using its unique 800v architecture. While Cybertruck can already hit 325kW from V3+ Superchargers, this is the next step forward to making Tesla's charge even faster.
Tesla Solar, Powerwall, and Megapack
Solar, Powerwall, and Megapack have been dutifully plodding away in the background, and Tesla has been working on expanding the factories that produce them. Both Mega Lathrop in the US and Mega Shanghai are undergoing expansions, and Tesla has released financial guidance that Megapack and Powerwall are going to be some of their biggest businesses.
Solar, on the other hand, seems to be slowly dying off. Tesla has killed off all their first-party solar installation and instead handed off the Tesla Solar program to third-party installers. There is also no news of pushing the Tesla Solar Roof to other countries - for now, it is only available in the United States “officially’.
We’d love to see Solar Roof and Tesla Solar make their way to other countries and even see some progress on the rumored Tesla home heat pump. While existing heat pumps are functional, Tesla has a way of disrupting industries and making them work smarter and harder like no one else.
Optimus
Tesla’s humanoid robot has made a big splash at the We, Robot event, and now we’ve even seen it starting to walk on its own. Tesla has also started to deploy Optimus to do some basic tasks at its factories in Texas.
Optimus is going to be another big game-changer, but this one is still years out. For now, we’d like to see more of the updated Optimus hands, and more of Optimus doing daily tasks, whether it's just walking, folding clothes, or tightening some bolts down.
Optimus is a fantastic future vision for Tesla, and it’ll definitely be something to keep an eye on in 2025. Who knows, maybe we’ll get another autonomy event from Tesla in 2025 where we’ll learn more about Optimus.
To wrap up this wishlist, there’s a lot to look forward to. 2024 was a fantastic year, and Tesla really hit most of their milestones. We saw amazing progress in FSD, the Cybertruck, and Model 3 Highland really settled in, and now there’s so much more to look forward to.
![Video Reveals the Cybertruck's Unique User Interface [Video]](https://www.notateslaapp.com/images/news/2023/cybertruck-ui-1_300w.jpg)
