Tesla has expanded its Full Self-Driving Beta program by releasing the first public version of FSD Beta 12.1.2, update 2023.44.30.12 to a select group of Tesla owners. This version is notable for its use of an end-to-end neural network, which is expected to greatly improve Tesla's advanced driver assist system (ADAS). The neural network, trained on millions of video clips, replaces much of the previous explicit C++ coding, improving the system's capability to handle complex driving situations. While Elon Musk had suggested that version 12 would see FSD coming out of beta, the release notes still label it as beta.
Tesla previously released FSD Beta v12 internally, including v12, v12.1, and v12.1.1, but v12.1.2 is the first to be available to non-employees. OG FSD Beta tester, and Tesla influencer, @WholeMarsBlog received this newest release last night and has already published his video (below).
Early Feedback & Tempering Expectations
Early reports say that FSD Beta v12 is more intuitive and drives more human-like. The feedback appears to be overwhelmingly positive, although it’s not uncommon for owners to get excited about such a monumental release that we’ve been looking forward to for many months. We may need to temper our expectations as this release alone won’t get us to level 4 or even level 3 autonomy, but it could be a significant step in the right direction. It could be as significant to vehicle control as when Tesla first transitioned to using AI for Autopilot.
Early reports say that there is a noticeable improvement in how the vehicle handles urban driving scenarios. The smoother transitions and quicker response times appear to contribute to a more comfortable and human-like driving experience. This shouldn’t be unexpected, as vehicle control is now trained on videos of humans driving instead of engineer-written code.
New Pull-Over Feature
A notable feature of FSD Beta v12.1.2 is its ability to pull over to the side of the road autonomously, a functionality showcased in Musk's live stream. At the end of a drive, the vehicle will now pull over to the site of the road instead of simply stopping. WholeMarsBlog shows off this feature in action in his video below:
For such a milestone release, Tesla hasn’t provided much information in the way of release notes. Each FSD Beta release normally contains a long list of technical release notes, which often need to be translated for everyone to understand. However, this time we get a single sentence that describes FSD Beta v12. The release notes simply state:
“FSD Beta v12 upgrades the city-streets driving stack to a single end-to-end neural network trained on millions of video clips, replacing over 300k lines of explicit C++ code.”
Road Ahead and Release Date
A clearer picture of FSD Beta v12.1.2 and its real-world performance will emerge as more Tesla owners receive the update and share their feedback. It will be interesting to see how the system handles diverse driving conditions, especially in areas with heavy precipitation, a scenario Elon Musk mentioned needing more training.
While this public release is monumental, the release to additional owners is expected to be a gradual and slow process. It could be months before most owners have access to this latest update. Tesla will likely gather feedback with this release and issue additional v12 betas to ignore other issues and improve the system.
While Tesla continues to innovate and refine its FSD technology, it is crucial to remember that the software is still in beta. The transition to full autonomy is a complex and gradual process, requiring rigorous testing and validation. However, with each update like v12.1.2, Tesla moves closer to realizing its vision of fully autonomous vehicles.
Subscribe
Subscribe to our newsletter to stay up to date on the latest Tesla news, upcoming features and software updates.
Tesla software update 2024.44.3 has started rolling out to customers in larger waves recently and it brings several new features - including Actually Smart Summon to Europe and the Middle East, as well as improvements to Autopark. But that’s not all, it also adds a new Blind Spot Monitoring feature to the new Model 3, and potentially the Cybertruck, but that’s still to be determined.
We previously covered the Blind Spot Warning While Parked as part of our preview notes for update 2024.44, but now that it's going out to customers, it's time to see it in action.
If the vehicle’s door open button is pressed, and a vehicle or object is near or incoming, the vehicle’s Blind Spot Warning Light (2024 Model 3 and Cybertruck) will illuminate, an audible tone will ring and the door won’t open. A message will also be displayed on the center displaying, letting driver’s know why the door didn’t open.
Pressing the button a second time will allow you to override the warning and open the door normally, providing a way to get out in case you just parked close to a nearby vehicle or obstacle.
The object detection for this new feature includes cars, pedestrians, cyclists, and other objects - like things including traffic cones, bollards, strollers, and other large obstacles that FSD and vision-based Autopark detect during normal operation. Of note - this only works for the front two doors. Thanks to X user Max, who did some testing for us, It does not work for the rear passenger doors.
Optional Feature
The feature is optional - it’ll be enabled by default for safety, but if you need to enable or disable it, you can do so under Controls > Safety. For now, the feature is only available on the 2024 Model 3, but we expect it to roll out to the Cybertruck at least. However, there’s no reason why it can’t be added to other vehicles as well, minus the small red dot. We expect Tesla to eventually add this feature to all Tesla vehicles, but it’s currently not a part of update 2024.44.
Enhauto’s S3XY Buttons & Commander
If that’s not enough safety and vision for you, Enhauto, the makers of the popular S3XY Buttons and Commander recently put out a new software update for the 2024 Model 3, which makes some fantastic use of the ambient lighting.
With Enhauto’s solution, users are able to tie their ambient lights to Autopilot use, turn signals or even if a vehicle is their blind spot. Check out the video below for this awesome implementation, where the ambient lights turn red when another vehicle approaches.
Maybe Tesla will integrate something like this into a future update? We’ve been hoping for more customizability with their ambient lighting - it's an easy safety win and a demonstration of Tesla’s do-more-with-less attitude.
I look forward to @enhauto updates more than Tesla...
Ambient light effects....
I set default color to white. Blinks green on turn signals Turns blue on FSD activation Yellow if someone in blind spot Blinks red if turn signal on and blind spot activity detected.
The feature is now possible thanks to what Wes Morrill, Cybertruck’s lead engineering, points out is a huge rewrite of Tesla’s Trip Planner, which not only makes it much more accurate but will now allow users to choose their arrival charge percentage.
More Accurate Trip Planner
When you navigate to a destination, your Tesla will automatically calculate when, where, and how much you need to charge. While the process seems straightforward, Tesla deserves a lot of credit for creating a simple user experience because a lot goes into accurately determining this information.
Tesla has to calculate many moving pieces in order to accurately predict when and where you should stop. First, it needs to consider your driving efficiency and wind direction, terrain elevation, traffic, vehicle speed, and ambient temperature. It also needs to predict the best Superchargers to stop at, taking into account congestion and charger speed.
This morning, in response to Dan Burkland, Wes shared that Tesla had significantly rewritten the backend portion of Trip Planner. These improvements, made by several engineers, were designed to improve Trip Planner’s accuracy and open the door to future features.
It sounds like these changes are mostly server-side, so thanks to their OTA connection, more accurate predictions should be available to all vehicles—no vehicle update is required.
Arrival State of Charge
Along with Tesla’s improvements to Trip Planner, Wes also stated that these improvements allow for a popular feature request — the ability to select your desired charge level at arrival.
Up until now, Tesla’s Trip Planner tried to get you to your destination as quickly as possible, which usually meant arriving with a low state of charge.
While this was fine if you have a charger at your destination, it’s not great if you don’t, or it could be even worse if there are no chargers nearby.
Max de Zegher said on X that he has heard the requests for a selectable arrival state of charge. Wes later clarified this by saying that these improvements to Tesla’s Trip Planner now allow for additional features to be added, such as “desired arrival charge.”
Actually trip planner got a huge rewrite on the back end. I had a great conversation with one of the engineers working on this over a morning run a few weeks back, it's pretty neat. The rewrite also unlocks additional features, like desired arrival charge.
Given that Max de Zegher’s comments came last night and Wes Morrill commented this morning, this feature request likely won’t arrive with the upcoming Holiday Update. Tesla actually hinted at such a feature being added in their last app update, so it does seem like they’ve already planned for it.
Although ‘Arrival State of Charge’ was on our wishlist for the Holiday Update, it looks like it may arrive soon after the holidays.
![First Look at Tesla’s New 'Blind Spot While Parked' Feature [VIDEO]](https://www.notateslaapp.com/img/containers/article_images/model-3-2024/blind-spot-indicator-monitor.jpg/4cdcb11af7b1c7cf021ba96588fd4f1a/blind-spot-indicator-monitor.jpg)
