If you hop into your Tesla and say ‘Hi’ or ‘Hello’ after pressing the Voice Command button, there is a good chance it’ll reply with “Hello!” This is the newest and most interesting piece of news pointing us to the conclusion that a Tesla voice assistant is on the way.
Previously, if you tried this, it would simply return “Command not understood.” This is the first time the vehicle is responding and interacting with the user.
Experience It Yourself
You’ll need to have your vehicle language set to English. Once that’s done, you can use the voice command button on your steering wheel or yoke - for the Model 3 and Model Y, push the right wheel button, and for the Model S, Model X, and Cybertruck, press the button. Then go ahead and say Hi or Hello.
The Hello! response may even have regional differences. For a German Tesla owner, after setting his language to English, the response came back as “Hallo.” We’re interested to see what the responses may be in other regions, so let us know if you notice anything interesting.
We’ve tried a few other basic things, but it seems that, for now, the vehicle only replies to a simple greeting. Asking it what time it is or the $TSLA stock price doesn’t seem to do much yet - unless you’re in China with the updated Smart Assistant.
Not a Tesla App
Server-Side Update
This update appears to be happening over Tesla’s voice system backend and doesn’t require the Holiday Update. Users who aren’t on the Holiday Update are reporting that they’re getting this new response as well.
We already know that Tesla interprets speech remotely, and the driver’s voice is not processed in the vehicle. Instead, the voice snippet is transmitted to Tesla’s servers, where Tesla processes it and sends a response back to the vehicle so that the vehicle can interpret it. This is unlikely to change with a smart assistant, as Elon Musk has already said that Grok will still process data server-side instead of on-device.
Many users recently also noticed significant improvements to voice commands, saying that the system understands them better and that responses now come back faster.
All of these things point to a new backend system for voice processing that Tesla is testing. It’s not unusual for a company to switch to a new backend process but keep the capabilities the same as the legacy system until it’s ready to roll out the new features. At that point, it’s simply a flip of a switch to allow the new capabilities.
The new smart assistant that was rolled out in China is mostly a backend change, with the in-vehicle experience largely remaining the same. The activation method (button press) and user interface remain the same. What changed is the response that comes back from the server, and the assistant gained a voice. The new voice we receive with a smart assistant could very well be the new voice users are experiencing in the navigation system in newer vehicles.
Below is a video of the voice assistant in China:
Vehicle Support - Intel?
When China received the Smart Assistant, it was locked to cars equipped with AMD Ryzen processors only. Shortly after its initial launch, it became available to older cars with Intel Atom processors as well.
However, we’re not sure whether it would apply to legacy Model S and Model X owners. A legacy vehicle owner had their vehicle report “Command not understood” when they tried the ’Hi’ voice command.
Grok for Tesla
Elon has previously mentioned that Tesla vehicles would receive Grok AI. Grok, as of yet, still doesn’t have live speech support like other LLM models such as OpenAI’s ChatGPT or Google’s Gemini. However, a major update to Grok just brought massively improved image generation via a new model called Aurora.
xAI has been hard at work improving Grok, and we’re sure that live speech support is on its way soon. Once that feature arrives on X, Tesla will likely be well-positioned to enable a Grok-powered smart assistant fleet-wide with a flick of a switch.
Ordering a New Tesla?
Consider using our referral code (nuno84363) to get up to $2,000 off your new Tesla and get 3 Months of FSD for free.
Tesla launched two FSD updates simultaneously on Saturday night, and what’s most interesting is that they arrived on the same software version. We’ll dig into that a little later, but for now, there’s good news for everyone. For Hardware 3 owners, FSD V12.6.1 is launching to all vehicles, including the Model 3 and Model Y. For AI4 owners, FSD V13.2.4 is launching, starting with the Cybertruck.
FSD V13.2.4
A new V13 build is now rolling out to the Cybertruck and is expected to arrive for the rest of the AI4 fleet soon. However, this build seems to be focused on bug fixes. There are no changes to the release notes for the Cybertruck with this release, and it’s unlikely to feature any changes when it arrives on other vehicles.
FSD V12.6.1 builds upon V12.6, which is the latest FSD version for HW3 vehicles. While FSD V12.6 was only released for the redesigned Model S and Model X with HW3, FSD V12.6.1 is adding support for the Model 3 and Model Y.
While this is only a bug-fix release for users coming from FSD V12.6, it includes massive improvements for anyone coming from an older FSD version. Two of the biggest changes are the new end-to-end highway stack that now utilizes FSD V12 for highway driving and a redesigned controller that allows FSD to drive “V13” smooth.
It also adds speed profiles, earlier lane changes, and more. You can read our in-depth look at all the changes in FSD V12.6.
Same Update, Multiple FSD Builds
What’s interesting about this software version is that it “includes" two FSD updates, V12.6.1 for HW3 and V13.2.4 for HW4 vehicles. While this is interesting, it’s less special when you understand what’s happening under the hood.
The vehicle’s firmware and Autopilot firmware are actually completely separate. While a vehicle downloading a firmware update may look like a singular process, it’s actually performing several functions during this period. First, it downloads the vehicle’s firmware. Upon unpacking the update, it’s instructed which Autopilot/FSD firmware should be downloaded.
While the FSD firmware is separate, the vehicle can’t download any FSD update. The FSD version is hard-coded in the vehicle’s firmware that was just downloaded. This helps Tesla keep the infotainment and Autopilot firmware tightly coupled, leading to fewer issues.
What we’re seeing here is that HW3 vehicles are being told to download one FSD version, while HW4 vehicles are being told to download a different version.
While this is the first time Tesla has had two FSD versions tied to the same vehicle software version, the process hasn’t actually changed, and what we’re seeing won’t lead to faster FSD updates or the ability to download FSD separately. What we’re seeing is the direct result of the divergence of HW3 and HW4.
While HW3/4 remained basically on the same FSD version until recently, it is now necessary to deploy different versions for the two platforms. We expect this to be the norm going forward, where HW3 will be on a much different version of FSD than HW4. While each update may not include two different FSD versions going forward, we may see it occasionally, depending on which features Autopilot is dependent on.
Thanks to Greentheonly for helping us understand what happened with this release and for the insight into Tesla’s processes.
At the 2025 Consumer Electronics Show, Nvidia showed off its new consumer graphics cards, home-scale compute machines, and commercial AI offerings. One of these offerings included the new Nvidia Cosmos training system.
Nvidia is a close partner of Tesla - in fact, they produce and supply the GPUs that Tesla uses to train FSD - the H100s and soon-to-be H200s, located at the new Cortex Supercomputing Cluster at Giga Texas. Nvidia will also challenge Tesla’s lead in developing and deploying synthetic training data for an autonomous driving system - something Tesla is already doing.
However, this is far more important for other manufacturers. We’re going to take a look at what Nvidia is offering and how it compares to what Tesla is already doing. We’ve done a few deep dives into how Tesla’s FSD works, how Tesla streamlines FSD, and, more recently, how they optimize FSD. If you want to get familiar with a bit of the lingo and the background knowledge, we recommend reading those articles before continuing, but we’ll do our best to explain how all this synthetic data works.
Nvidia Cosmos
Nvidia’s Cosmos is a generative AI model created to accelerate the development of physical AI systems, including robots and autonomous vehicles. Remember - Tesla’s FSD is also the same software that powers their humanoid robot, Optimus. Nvidia is aiming to tackle physical, real-world deployments of AI anywhere from your home, your street, or your workplace, just like Tesla.
Cosmos is a physics-aware engine that learns from real-world video and builds simulated video inputs. It tokenizes data to help AI systems learn quicker, all based on the video that is input into the system. Sound familiar? That’s exactly how FSD learns as well.
Cosmos also has the capability to do sensor-fused simulations. That means it can take multiple input sources - video, LiDAR, audio, or whatever else the user intends, and fuse them together into a single-world simulation for your AI model to learn from. This helps train, test, and validate autonomous vehicle behavior in a safe, synthetic format while also providing a massive breadth of data.
Data Scaling
Of course, Cosmos itself still requires video input - the more video you feed it, the more simulations it can generate and run. Data scaling is a necessity for AI applications, as you’ll need to feed it an infinite amount of data to build an infinite amount of scenarios for it to train itself on.
Synthetic data also has a problem - is it real? Can it predict real-world situations? In early 2024, Elon Musk commented on this problem, noting that data scales infinitely both in the real world and in simulated data. A better way to gather testing data is through real-world data. After all, no AI can predict the real world just yet - in fact, that’s an excellent quantum computing problem that the brightest minds are working on.
Yun-Ta Tsai, an engineer at Tesla’s AI team, also mentioned that writing code or generating scenarios doesn’t cover what even the wildest AI hallucinations might come up with. There are lots of optical phenomena and real-world situations that don’t necessarily make sense in the rigid training sets that AI would develop, so real-world data is absolutely essential to build a system that can actually train a useful real-world AI.
Tesla has billions of miles of real-world video that can be used for training, according to Tesla’s Social Media Team Lead Viv. This much data is essential because even today, FSD encounters “edge cases” that can confuse it, slow it down, or render it incapable of continuing, throwing up the dreaded red hands telling the user to take over.
Cosmos was trained on approximately 20 million hours of footage, including human activities like walking and manipulating objects. On the other hand, Tesla’s fleet gathers approximately 2,380 recorded minutes of real-world video per minute. Every 140 hours - just shy of 6 days - Tesla’s fleet gathers 20 million hours of footage. That was a little bit of back-of-the-napkin math, calculated at 60 mph as the average speed.
Generative Worlds
Both Tesla’s FSD and Nvidia’s Cosmos can generate highly realistic, physics-based worlds. These worlds are life-like environments and simulate the movement of people and traffic and the real-life position of obstacles and objects, including curbs, fences, buildings, and other objects.
Tesla uses a combination of real-world data and synthetic data, but the combination of data is heavily weighted to real-world data. Meanwhile, companies who use Cosmos will be weighting their data heavily towards synthetically created situations, drastically limiting what kind of cases they may see in their training datasets.
As such, while generative worlds may be useful to validate an AI quickly, we would argue that these worlds aren’t as useful as real-world data to do the training of an AI.
Overall, Cosmos is an exciting step - others are clearly following in Tesla’s footsteps, but they’re extremely far behind in real-world data. Tesla has built a massive first-mover advantage in AI and autonomy, and others are now playing catch-up.
We’re excited to see how Tesla’s future deployment of its Dojo Supercomputer for Data Labelling adds to its pre-existing lead, and how Cortex will be able to expand, as well as what competitors are going to be bringing to the table. After all, competition breeds innovation - and that’s how Tesla innovated in the EV space to begin with.
