Last week, the Ride the Lightning podcast interviewed Tesla’s VP of Vehicle Engineering, Lars Moravvy. We learned quite a bit from that episode, including the fact that Tesla is working on refreshing the Model S and X.
In this week’s episode, they interviewed Tesla’s Chief Vehicle Designer, Franz von Holzhausen, and there’s another treasure trove of information to enjoy here. This is also the 500th episode of Ride the Lightning, so if you haven’t heard of them, be sure to check them out (video below).
New Paint Colors
Tesla has replaced many of its original colors throughout the years, but it hasn’t really introduced new ones. Franz mentioned that the public weeds out the color choices - so when a color just isn’t ordered, Tesla drops it from its lineup. This includes the browns and the greens.
Meanwhile, black, white, and greys are the vast majority of what people order. The blue and the red are also equally popular. However, adding more colors increases complexity. Certain paints require multiple coats or different spray nozzles - it all adds up to additional complexity.
Colors take a while to develop, too - it takes time to establish the process, develop the color, and make sure the color will last and stay stunning. Each paint also needs to pass durability testing - and different pigments can withstand different things. This is actually why Tesla is going away from paint in the Robotaxi and they’ll instead infuse pigment into the plastic panels themselves.
Glacier Blue
Glacier Blue is the 3rd blue that Tesla has produced - and it’s the lightest color of all the choices. Tesla had been refining this color for some time, experimenting with pigmenting to add depth and character to the silver tones. The result was Glacier Blue, which ultimately found its way to the refreshed Model Y.
Franz avoided answering whether Glacier Blue is coming to North America, but Tesla’s engineering team previously hinted that new colors are coming to North America. It’s likely that Glacier Blue, or some variant of it, will be one of the new colors. Franz also declined to answer whether Midnight Cherry Red - the beautiful red variant in Europe - would be discontinued. He said it was a really beautiful color and that Tesla had spent a lot of time on that color - and that he had to “stay tuned.”
Roadster Sneak Peak
Tesla’s 2nd Gen Roadster has been a bit of a mystery. It was supposed to be a technology showcase - an EV to bring a smackdown to every other vehicle. It also served as a tech testbed - and the tech on the 2017 Roadster prototype eventually made its way down to other vehicles - like the Model S Plaid.
The Roadster should be exciting and capture everyone’s imagination. It should be a car that captures kids’ imaginations, one they have posters of and dream of owning one day. We last heard about the Roadster almost exactly a year ago, with Musk stating that Tesla radically increased the design goals for the vehicle. At the time, Musk said deliveries would be in 2025, but that seems like a pipedream right now, and maybe rightly so. Although the Roadster will undoubtedly be a marvel, it’ll be a very low-volume vehicle. If Tesla wants to continue to reach the masses, it will need to start production on its next-gen, lower-priced vehicle and roll out Robotaxi.
The Roadster serves as Tesla’s racing program, developing and testing what will eventually be integrated into other vehicles. How about cold-rocket boosters on a Cybertruck?
Challenges with Optimus
Optimus may not be a car, but Tesla’s chief designer, Franz von Holzhausen, and his team are deeply involved in shaping its design. Tesla’s designers are pushing creative boundaries to rethink what a humanoid robot can be.
The goal is to replicate the human form—a challenge that’s as much artistic as it is technical. The complexity of the human body makes this a difficult task, requiring precision in both mechanics and aesthetics.
To achieve this, Tesla has developed custom-designed actuators and joints, refining Optimus to better fit the humanoid form. Unlike traditional design and engineering teams that often work in silos, Tesla’s designers and engineers collaborate closely, allowing them to tackle and overcome challenges together.
The Affordable Model
Tesla’s mission with its products is simple: each one should feel like a premium purchase, offering more value than what you paid for it. Whether it’s an affordable model or a high-end one, Tesla is committed to creating products that are built to last, beautifully designed, and deliver exceptional performance.
This means exploring innovative materials that make their more affordable products still feel premium. Interestingly, Franz mentions the word “products” multiple times here - something he didn’t really do in other parts of the interview.
This was a fantastic interview with Franz that gave us a closer look at how Tesla works and what they have in the pipeline. Be sure to check it out below.
Tesla has just released software update 2025.8 to employees for testing. This is the norm for Tesla, as they release software updates to their internal audience for testing before beginning a rollout to the public.
While we don’t know what’s in this update just yet, there are several features we know that are coming up and could be included.
Adaptive Headlight Support
Tesla’s VP of Vehicle Engineering, Lars Moravy, recently confirmed that the refreshed Model Y will receive adaptive headlights, as well as the matrix headlight functionality. In fact, it’ll be the first vehicle in Tesla’s line-up that will support matrix headlights in North America.
The feature just received approval in the United States recently and will be rolling out to all Tesla vehicles that have matrix headlights sometime soon. That includes support for the Cybertruck, and Model S, Model X, and Model 3 as well.
Grok Support
xAI recently launched the newest version of their smart assistant - Grok 3. That same smart assistant is eventually supposed to make its way over to Tesla vehicles, according to Elon Musk.
The new smart assistant is expected to provide quite a bit of new functionality when it comes to intelligently handling your voice commands, and it could be included in this upcoming update, although a Spring launch is more likely. Grok 3 just launched voice support last week.
Cybertruck Updates
Siddhant Awasthi, Tesla’s Cybertruck program manager, recently confirmed that a new set of suspension controls are on their way to the Cybertruck. As of now, you can only adjust the vehicle’s height in the vehicle.
We’re hoping this new feature allows access to vehicle height adjustments from the Tesla App, as well as unlocking some new vehicle drive heights in general.
One of the items that didn’t manage to make it into 2025.2 was the Cold Weather Fix for the Cybertruck. Certain Cybertrucks have issues reaching max charging speed due to not properly pre-conditioning in cold weather when plugged into an L2 charger, and some Cybertrucks are also seeing drastically reduced regen in those temperatures, too. Hopefully, this will also get tackled in update 2025.8.
In-Cabin Radar Support
Tesla has started to activate the in-cabin radar in older Model Y vehicles that have it equipped, but it has confirmed that other equipped models will eventually also receive support. The in-cabin radar replaces the front seat occupancy sensors and instead uses the radar to more accurately detect the presence of humans.
New navigation routing options were released for Chinese users in early January, which included new options such as Least Congestion, Prefer Highways, and Lowest Tolls. It also brought with it a new Service Area modal, which shows what amenities are available at various vehicle service areas on the highways.
We’re hoping to receive at least some of these features in North America and Europe sometime soon. We’ve been waiting for that Avoid Highways option for what seems like an eternity now.
Trailer Profiles for Model S, X, Y
Trailer Profiles launched with the Cybertruck, and are, for now, an exclusive feature. Hopefully, the ability to save trailer details will make its way to other tow-hitch-compatible vehicles. Trailer Profiles allow you to save information about your trailer, including type and braking settings - which can help more accurately estimate energy usage. In addition, it is an easy way to track trailer mileage.
Custom Vehicle Wraps for Models S, 3, X, Y
With the 2024 Holiday Update, Tesla gave the ability to wrap the Cybertruck in whatever style you wanted - in the vehicle visualization. Many people used it to match the actual wraps or decals they had on their vehicles. This functionality also covered license plates - including custom styles, numbering, and lettering.
Tesla later confirmed these wrap and license visualizations would eventually roll their way out to the rest of the fleet, so we’re expecting them to either in 2025.8 or shortly after.
Sentry Mode Efficiency Update
Back in November 2024, Tesla made some significant improvements to the Cybertruck’s Sentry Mode. They achieved an almost 40% reduction in the overall energy usage of Sentry Mode by making better use of the onboard vehicle compute.
These updates should soon roll out to the rest of the fleet, greatly improving Sentry Mode efficiency.
Release Date
In general, Tesla takes between one to two weeks to release an update to customers after sending it to wave 1 employees. That timeline isn’t firm - so sometimes it could take five days, and sometimes it could take the full two weeks, but the clock is ticking for this one now. We should have the full release notes in the next week or two and then our first look at some of the new features in the following days.
We previously dived into how FSD works based on Tesla’s patents back in November, and Tesla has recently filed for additional patents regarding its training of FSD.
This particular patent is titled “Predicting Three-Dimensional Features for Autonomous Driving” - and it’s all about using Tesla Vision to establish a ground truth - which enables the rest of FSD to make decisions and navigate through the environment.
This patent essentially explains how FSD can generate a model of the environment around it and then analyze that information to create predictions.
Time Series
Creating a sequence of data over time - a Time Series - is the basis for how FSD understands the environment. Tesla Vision, in combination with the internal vehicle sensors (for speed, acceleration, position, etc.,) establishes data points over time. These data points come together to create the time series.
By analyzing that time series, the system establishes a “ground truth” - a highly accurate and precise representation of the road, its features, and what is around the vehicle. For example, FSD may observe a lane line from multiple angles and distances as the vehicle moves through time, allowing it to determine the line’s precise 3D shape in the world. This system helps FSD to maintain a coherent truth as it moves forward - and allows it to establish the location of things in space around it, even if they were initially hidden or unclear.
Author’s Note
Interestingly, Tesla’s patent actually mentions the use of sensors other than Tesla Vision. It goes on to mention radar, LiDAR, and ultrasonic sensors. While Tesla doesn’t use radar (despite HD radars being on the current Model S and Model X) or ultrasonic sensors anymore, it does use LiDAR for training.
However, this LIDAR use is for establishing accurate sensor data for FSD - for training purposes. No Tesla vehicle is actually shipped with any LiDAR sensors. You can read about Tesla’s use for its LIDAR training rigs here.
Associating the Ground Truth
Once the ground truth is established, it is linked to specific points in time within the time series - usually a single image or the amalgamation of a set of images. This association is critical - it allows the system to predict the complete 3D structure of the environment from just that single snapshot. In addition, they also serve as a learning tool to help FSD understand the environment around it.
Imagine FSD has figured out the exact curve of a lane line using data from the time series. Next, it connects this knowledge to the particular image in the sequence where the lane line was visible. Next, it applies what it has learned - the exact curve, and the image sequence and data - to predict the 3D shape of the line going forward - even if it may not know for sure what the line may look like in the future.
Author’s Note
This isn’t part of the patent, but when you combine that predictive knowledge with precise and effective map data, that means that FSD can better understand the lay of the road and plan its maneuvers ahead of time. We do know that FSD takes into account mapping information. However, live road information from the ground truth is taken as the priority - mapping is just context, after all.
That is why when roads are incorrectly mapped, such as the installation of a roundabout in a location where a 4-way stop previously existed, FSD is still capable of traversing the intersection.
Three Dimensional Features
Representing features that the system picks up in 3D is essential, too. This means that the lane lines, to continue our previous example, must move up and down, left and right, and through time. This 3D understanding is vital for accurate navigation and path planning, especially on roads with curves, hills, or any varying terrain.
Automated Training Data Generation
One of the major advantages of this entire 3D system is that it generates training data automatically. As the vehicle drives, it collects sensor data and creates time series associated with ground truths.
Tesla does exactly this when it uploads data from your vehicle and analyzes it with its supercomputers. The machine learning model uses all the information it gets to better improve its prediction capabilities. This is now becoming a more automated process, as Tesla is moving away from the need to manually label data and is instead automatically labeling data with AI.
Semantic Labelling
The patent also discusses the use of semantic labeling - a topic covered in our AI Labelling Patent. However, a quick nitty-gritty is that Tesla labels lane lines as “left lane” or “right lane,” depending on the 3D environment that is generated through the time series.
On top of that, vehicles and other objects can also be labelled, such as “merging” or “cutting in.” All of these automatically applied labels help FSD to prioritize how it will analyze information and what it expects the environment around it to do.
How and When Tesla Uploads Data
Tesla’s data upload isn’t just everything they may catch - even though they did draw an absolutely astounding 1.28 TB from the author’s Cybertruck once it received FSD V13.2.2. It is based on transmitting selective sensor information based on triggers. These triggers can include incorrect predictions, user interventions, or failures to correctly conduct path planning.
Tesla can also request all data from certain vehicles based on the vehicle type and the location - hence the request for the absurd 1.28 TB coming from one of the first Canadian Cybertrucks. This allows Tesla to collect data from specific driving scenarios - which it needs to help build better models that are more adaptable to more circumstances while also keeping data collection focused, thereby making training more efficient.
How It Works
To wrap that all up, the model applies predictions to better navigate through the environment. It uses data collected through time and then encapsulated in a 3D environment around the vehicle. Using that 3D environment, Tesla’s FSD formulates predictions on what the environment ahead of it will look like.
This process provides a good portion of the context that is needed for FSD to actually make decisions. But there are quite a few more layers to the onion that is FSD.
Adding in Other Layers
The rest of the decision-making process lies in understanding moving and static objects on the road, as well as identifying and reducing risk to vulnerable road users. Tesla’s 3D mapping also identifies and predicts the pathing of other moving objects, which enables it to conduct its path planning. While this isn’t part of this particular patent per-say, it is still an essential element to the entire system.
If all that technical information is interesting to you, we recommend you check out the rest of our series on Tesla’s patents:
We’ll continue to dive deep into Tesla’s patents, as they provide a unique and interesting source to explain how FSD actually works behind the curtains. It’s an excellent chance to get a peek behind the silicon brains that make the decisions in your car, as well as a chance to see how Tesla’s engineers actually structure FSD.
![Andrej Karpathy considers returning to Tesla to work on Optimus [video]](https://www.notateslaapp.com/images/news/2022/karpathy-podcast_300w.jpg)
