Tesla has released the much-anticipated new Autopark feature that is expected to be based on the new neural networks that power FSD Beta v12.
Teslas have had Autopark capability for several years, although it has several shortcomings, besides not being available to any recent vehicles that do not include ultrasonic sensors (USS).
This refined version of Autopark is available as part of update 2024.2.11, although the update appears to be limited to employees at this time.
This new iteration of Autopark is expected to be a big improvement over the previous version. According to Musk, it contains “major improvements” over the previous version.
Video
Update: The first video of the new Autopark feature is now available thanks to X user Space Cat, who drives a Model Y with Enhanced Autopilot and without ultrasonic sensors. In the video below you can see the new parking visuals and how easily the vehicle detects parking spots, something the current Autopark feature struggles with.
The driver can pick from any of the highlighted spots. It’s impressive how the vehicle shifts to drive or reverse depending on what’s needed. This appears to be similar behavior to what we’ll see in FSD, according to Tesla’s Autopilot director.
Tesla made the process to initial Autopark easy with this release. The vehicle automatically displays available parking spots and defaults to one nearby. All the driver has to do is stop the vehicle and tap ‘Start’ on the screen to start Autopark. There’s no need to tap a button to have the vehicle detect parking spots or even to select a particular spot, unless you have a preference.
Musk has been talking about the new ‘Tap to Park’ feature for several months. In December 2023, Musk said "We are working on a feature where the car identifies probable viable parking spaces. You tap on one, exit the vehicle and it parks there."
The release notes in this version don't mention the ability to exit the vehicle before the vehicle starts parking, although it sounds like that's Tesla's goal for this feature. This first iteration could be Tesla's MVP (Minimal Viable Product) that they'd like to ship and they'll slowly add on features as the feature is refined.
There are several hints beyond Musk's comment that Tesla will eventually support tapping a parking spot on the screen and allow the driver to exit the vehicle while the car parks itself.
A look under the hood at Tesla's recent app update showed that Tesla is building Autopark features into the app, hinting that you may even be able to initiate Autopark directly from your phone in the future.
This is very similar to what you can already do with Summon on vehicles with USS. From your device, you can wake up the vehicle and have it drive a short distance to you. It's not far-fetched to think that Tesla has sights on being able to do this in reverse.
Available to Vehicles Without USS
Tesla has been delivering vehicles without USS, Autopark, and Smart Summon for over a year now. This updated feature is expected to have improved vision to make up for the lack of USS. A similar situation occurred with Park Assist, where vehicles without USS could no longer show distances to objects when parking.
Tesla then introduced High-Fidelity Park Assist in the holiday update and surprised everyone with what they were able to accomplish. Instead of just displaying distances to objects, Tesla created 3D models of surrounding objects and colored them based on the vehicle's proximity.
High-Fidelity Park Assist is still limited to vehicles without USS, but we know Tesla is working on adding the feature to vehicles that include ultrasonic sensors as well. It's not clear whether the new Autopark may also only be rolled out to vehicles without USS, or if it'll be available to all vehicles at the same time.
Autopark is part of Tesla’s Enhance Autopilot (EAP) suite, so only users with EAP or FSD are expected to receive the feature when it rolls out.
Improved Visuals and Selection
The image Tesla released shows an improvement in Autopark visuals. The current iteration of Autopark only shows one parking spot at once, and it's difficult to even have that come up on the screen.
This new version appears to be a drastic improvement, not only outlining a parking spot on the display but also displaying various parking spots at once - including parallel spaces.
According to the release notes, the parking spots will appear any time you're driving slowly through a parking lot, although the exact speed isn't specified.
Improved Autopark
Musk previously talked about a vast improvement in the new Autopark, which he called Tap to Park. This new Autopark is expected to be based on the same neural networks that power FSD Beta v12, which has been a drastic improvement over FSD Beta v11.4.9. We should see a much improved Autopark experience when this feature becomes available to Tesla owners.
Although the previous version of Autopark worked, it was difficult to have it detect a parking spot and display it on the screen. It often also parked very slowly, making it less almost useless if there were other vehicles around. However, the result was usually quite good, with the vehicle parking safely and well between the parking lines. We expect the two shortcomings of the current Autopark to be drastically improved in this latest revision.
Public Roll Out / Release Date
Just a few days ago, Musk revealed that Tesla would release a new version of Summon (Actually Smart Summon) and a new Autopark feature with "major improvements" next month (April).
It's surprising to see this feature added to update 2024.2.11 when Tesla is already rolling out 2024.8.4. This leads us to believe that this update may be currently in a testing phase with employees and is not yet ready to go to a public release.
When Tesla is ready to ship this feature to owners, we'll likely see it introduced in a revision to 2024.8, or even the next major update, which could be 2024.12.
Either way, it looks like we'll be getting it fairly soon, and if the new Autopark has anywhere near the improvements in Tesla's FSD Beta v12.3, then we're in for a real treat.
Subscribe
Subscribe to our newsletter to stay up to date on the latest Tesla news, upcoming features and software updates.
Tesla has been quietly building something pretty unique on the streets of Hollywood—and we’ve been keeping a close eye on it. That’s right: the long-anticipated Tesla Hollywood Drive-In, Diner, and Supercharger is shaping up to be one of the most creative approaches to EV charging yet.
But this isn’t your average Supercharger site. It features a retro-futuristic, 24-hour diner and an outdoor movie theater, blending the charm of the 1980s with the tech-forward vibe of the 2020s.
Tesla hacker Greentheonly managed to spot some new evidence of changes within Tesla’s 2025.8.6 software build, which includes a new modal for “Charger Diner Controls”. While there isn’t anything to activate this new modal just yet, it is an indication of how Tesla intends to integrate the experience right into each and every Tesla.
The text in the modal reads: “Plug in, place your order, recharge” - which means that once you arrive and are plugged in, you’ll be able to place your order - and likely pay through Tesla’s payment system. It seems like this will all be done through either the Tesla app or the vehicle’s tocuh screen. No need to fumble with a separate app or pull out your wallet.
This is definitely a level of integration you just can’t have anywhere else - and just like any other Supercharger site, the Tesla Diner will appear as a suggested site for charging when you’re navigating or looking around the Hollywood area.
This is our best look yet at the two 45-foot LED screens at @Tesla's upcoming Hollywood diner and Supercharger.
We can also see the second Supercharger lot on the left with solar canopies. This will be one of the largest Supercharging spots in North America. pic.twitter.com/aWUe67M5vw
Those two absolutely gigantic 45-foot LED screens have now been turned on for the first time, meaning that Tesla is likely close to opening the Supercharger site. The screens were spotted displaying some test patterns, as well as some Tesla-themed content. It really brings the construction site to life - and it's the clearest sign that the Diner is well on its way to completion.
We’re hoping that this first Tesla Diner sees plenty of success - and that Tesla begins opening more of these types of facilities throughout North America, and eventually globally. Given Tesla’s penchant for unique Superchargers, we imagine this could truly be the case one day.
As Tesla continues to push the capabilities of its hardware as it prepares for autonomy with FSD Unsupervised, there has been a distinct divergence in features between HW4-equipped vehicles on FSD V13, and HW3-equipped vehicles on FSD V12.6.
There are definitely reasons for this, and Tesla hacker Greentheonly, over on X, went into great detail on some of the reasons why this divergence has continued and is likely to continue.
If you’re interested in some background, we recommend the following articles. Although they’re not necessary, you may enjoy reading them before diving right in if you enjoy this topic.
Back in the summer of 2024, we reported that Tesla’s HW4 had yet to reach its full potential, and that HW3 still had some compute to work with. However, FSD has undergone a rapid evolution - there are now fundamental differences driven by the hardware capabilities and sheer scale of the latest builds of FSD.
FSD V13’s Gargantuan Neural Networks
FSD V13 is a substantial leap for Tesla. It features substantially larger neural networks - the core brain that processes all the environmental data and makes decisions. Those networks are far larger in V13 than in V12, which results in a much smoother and human-like expereience.
Tesla’s FSD computers contain two nodes. According to Green’s analysis of FSD V13, Node B, which handles the actual end-to-end driving logic, tripled in size from 2.3 GB in V12 to a staggering 7.5 GB in V13. That’s a substantial increase, and one of the main reasons why HW3 can’t handle FSD V13. While Interestingly, Node A on HW4 remains similar in size to FSD V12, using up about 2.3 GB.
However, this massive size is also pushing the limits of HW4. While this isn’t necessarily a big problem immediately - at the end of the day, there is a limited amount of compute and ram available and model sizes will likely grow in the future. In fact, Tesla is planning to scale model sizes in the next FSD version and has already said they’ll need to optimize them, as context size is limited by on-board memory.
HW3 Limitations
Since HW3 can’t run the latest FSD models, where does this leave millions of Tesla vehicles equipped with the now-legacy FSD hardware? Are they hitting a dead end? Not exactly - Tesla has promised to replace HW3 computers with new units during the Q4 2024 Earnings Call, but only for those who have purchased FSD and only if Tesla is no longer able to update HW3 vehicles.
There’s no doubt Tesla hopes to achieve autonomy and then work backwards to make it compatible with HW3, but that’s unlikely to happen with the limited ram available on HW3.
Tesla’s AI team has continued to say that they’re still working on updating HW3 vehicles - but that they will be taking a backburner to updates for HW4 until the team can optimize the model efficiently enough to run on the smaller footprint. That means V12.6 isn’t just V13 “lite” - it is a distinctly different software branch tailored specifically for HW3’s capabilities.
Green's analysis showed that HW3 under V12.6 runs NNs totaling 1.2 GB on Node A and 3.1 GB on Node B, which is significantly smaller than the footprint of V13. Back in November, we discussed how Tesla is running a smaller and optimized FSD model on HW3, with the specific goal of achieving similar performance to V13. FSD V12.6 appears to be the current implementation of that smaller model strategy.
Green also found that of the total neural nets used for FSD, 135 are shared between the current V12.6 and FSD V13.2 releases, which is the result of Tesla’s AI team working to optimize and refine the V13 model for HW3. So some neural nets are shared between the two sets of hardware, while others are specific to HW3 or HW4.
AI4 in the Future
The fact that V13 is already stretching HW4’s limits makes us wonder about Tesla’s imminent release of AI5. Last year, Tesla mentioned that AI5 would be 18 months away - which is now about 8 months away, and potentially even sooner to help solve the autonomy problem.
At the same time, Tesla is looking to launch Unsupervised FSD in June in Austin, Texas, with presumably HW4, which would indicate that they’re confident in its capabilities.
Unless Tesla launches the Robotaxi network with AI5, we don’t believe AI5 will be a “must have” item. Undoubtedly, it will result in similar improvements to HW4 compared to HW3. However, the software needed to take advantage of the newer hardware could still be years away.
All eyes will be on Tesla’s Robotaxi network launch and the hardware required for it. For now, HW4 owners are in good hands with future updates are on the horizon, and we’re certainly excited for what’s next.