Matrix headlights have a circular dome projector on the outer edge
Not a Tesla App
Tesla has been on a roll with updates recently, and now update 2024.20 was released to employees over the weekend. This update builds on the many features in the Spring Update and adds a few big improvements.
Adaptive Headlight Support in the US & Canada
Tesla recently tweeted that update 2024.20 is now rolling out to vehicles - and they included some surprises in this tweet. This update includes Adaptive Headlights for the United States and Canada! North America will receive adaptive headlight support by including the curve adaption feature discussed below. South Korea and Puerto Rico will also gain the feature.
Europe and possibly other regions will also include this feature in addition to being able to illuminate further on highways.
Tesla also shed some light on what’s included in the hot weather improvements. All Model 3s and Model Ys, as well as refreshed Model S and X’s will now cool down faster in hot temperatures. They will also better regulate high-voltage battery temperature for improved Supercharging performance. The Cybertruck in particular will also benefit from a quieter AC.
The full list of improvements in update 2024.20 is discussed below.
Update: This article has been updated to make it clearer that the U.S. and Canada did not receive full matrix headlight support. What they received was the ability for vehicles with matrix headlights to light up the sides of the road in response to upcoming turns. The Tesla release notes state:
“Headlights now adapt for curves in the road ahead for greater visibility in low lighting. Enable this feature in your vehicle settings at Lights > Adaptive Headlights.”
This differs from the European release notes for the same feature which state:
“Headlights now adapts for curves in the road ahead of you and illuminate farther when you’re driving on a motorway.”
“Enable these features in your vehicle settings at Lights > Adaptive Headlights.”
Adaptive Headlights
New updates to Adaptive Headlights are arriving for European cars with matrix headlights. The new update allows the headlights to adapt to curves in the road ahead of you, enabling better illumination. Having the adaptive headlights work for curves is the second major update for European headlights. Update 2024.8 added adaptive high-beam support, letting your high beams stay on longer by turning off select LEDs in the headlights.
Update 2024.2 first brought adaptive high beams to the new Model 3, before it was later introduced to older vehicles with matrix headlights. At this time, it’s not clear whether the improvements to headlights around curves will be exclusive to matrix headlights or also support the new Model 3.
How to Tell If You Have Matrix Headlights
How do you know if you have matrix headlights on your Tesla? On the outer edge of the headlight, there will be a large, round projector dome, like in the image below. If there isn’t a dome, those are standard non-matrix headlights. Another way to tell is to run a stock light show while facing a wall. If the Tesla logo, in letters, pops up, you have matrix headlights.
For now, North America still does not have adaptive headlight support, mostly due to legislative and testing issues in the United States. The US recently approved adaptive headlights, and a Tesla employee mentioned they’re working on it. Canada has legalized adaptive headlights since 2018, so we see this deployed in North America at some point in the future.
Supercharger Races on Beach Buggy Racing 2
Tesla is still improving its Arcade functionality, with the addition of local leaderboards at Superchargers in Beach Buggy Racing 2. It appears that each individual Supercharger site will have its own leaderboard, which drivers can compete on while their cars charge. Tesla says there will also be special races to compete in this Beach Buggy Racing 2 update.
Tesla owners can plug in and play with a controller, the touchscreen, or their vehicle’s steering wheel. Thanks to steer-by-wire on the Cybertruck, the actual wheels on the truck won’t move like they do on other Tesla models when playing the game.
We continue to hope that future refreshes to the S, 3, X, and Y will eventually receive steer-by-wire as well, as the feature has quite a few unique uses, whether driving or parked.
Autopilot Strikes and Suspension
An updated Autopilot Strike system, similar to the one that is on Tesla’s upcoming FSD V12.4 update, is on 2024.20 as well. At five strikes, users will be suspended from the use of Autopilot like before, but now Tesla will remove a strike for each 7-day period the driver goes without receiving a strike.
FSD 12.4 also improves vision-based monitoring and removes the steering wheel nag, but that’s not in this latest Tesla update, but will likely be added in the future.
Tesla tends to release new Autopilot features in their FSD updates before releasing them to the wider public for regular Autopilot use.
Hot Weather Improvements
The last set of user-end improvements coming in 2024.20 will be related to hot weather, the opposite of 2024.2.6’s cold weather update. This set of changes intends to improve AUTO mode HVAC performance in hot weather, helping to cool down the cabin faster, while also maintaining comfort at lower noise levels.
There have been several updates in the last six months to Tesla’s HVAC systems, all helping to deliver a quieter, more comfortable experience, with one of the last major ones introducing cool-down or warm-up periods before blowing air into the car cabin.
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.
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.
Last night, Tesla released software update 2024.45.25.15, which includes FSD V12.6.1. This update adds support for all HW3 vehicles, including the Model 3 and Model Y. We’re excited to see the continued support for HW3 owners.
FSD V12.6.1
V12.6.1 is now going wide, according to Ashok Elluswamy, Tesla’s VP of AI. This update is going to the Model 3 and Model Y for the first time - as only the Model S and Model X were included in FSD V12.6.
V12.6 is a big step forward for HW3 - it includes End-to-End on Highway, Improved City Streets Behavior, and Smoother and More Accurate Tracking - all contributing towards a better, smoother, and more comfortable build of FSD. You can read our comparison between FSD V12.6 and V13.2.2 here.
In short, FSD V12.6 performs considerably closer to V13 than V12.5.4.2 - which is a massive improvement. It performs as well as the Cybertruck version of FSD V13, which is still missing a few features when compared to other HW4 vehicles, but it’s a great sign for HW3. A lot of the improvements can be pointed to in the improvements to lane selection and decision-making - the vehicle tends to hesitate far less on V12.6, meaning the ride is a lot smoother. Many early V12.6 testers mentioned that it felt more like V13-mini than anything else.
Legacy Model S & X
We haven’t seen this update hit any legacy Model S and Model X vehicles just yet. We’re not sure whether Ashok’s statement of “generally” applies here - but it should. If you do get the update, please let us know.
Legacy Model S and Model X vehicles are still on an older FSD build and potentially won’t see another FSD update for a little while longer. While they do have the same FSD hardware as other vehicles, there are enough hardware differences that require a build specifically for these vehicles.
FSD V12.6.1 is going out now to the redesigned Model S and X with HW3 and all Model 3 and Model Y vehicles with HW3. The initial wave went out last night, and we expect to see more later today or tomorrow. If this release ends up going “wide,” we should see much larger waves go out next week.
![Tesla Adds HEPA Filter to New Model 3, Will it Get Bioweapon Defense Mode? [Update: Tesla Edits Post]](https://www.notateslaapp.com/images/news/2023/new-model-3-hepa-filter_300w.jpg)
_300w.png)
