Tesla's early FSD Betas included driving visualizations that used simple wireframe boxes to represent vehicles and lane markings were made up of individual dots.
Tesla adds scalable vehicle models to the latest FSD Beta
The visualizations were a great look into some of the information that is provided to Autopilot, but even then only a fraction of the information Autopilot uses was actually displayed onscreen.
In reality, Autopilot is creating a 3D representation of every object it tracks. Each object detected then has various attributes. For example, a detected vehicle will have attributes for how fast it's going, how far away it is, the type of vehicle, its predicted path, and more.
Tesla's visualizations in early FSD Betas
The car visualizations are an important part of FSD because they help us better understand what the car is capable of seeing and reacting to. However, the information and visualization Autopilot needs is drastically different than what humans need.
In order for Tesla to achieve FSD, they essentially need to be able to build a highly accurate video game that represents the real world, in real-time.
The car wants access to as much information about each object as possible. Meanwhile, humans want a visualization that closely resembles the real world.
With the introduction of FSD Betas 9.x, Tesla released a more human consumable visualization. One that included proper 3D models of general vehicle types, road pylons, and solid lane markers.
The road edges and lane markings are more distinguished lines, 3D models have working brake lights, and other objects such as speed bumps, bike lanes, and crosswalks are depicted using visualizations that match the real world.
In order for Tesla to achieve FSD, they essentially need to be able to build a highly accurate video game that represents the real world, in real-time.
However, something that has been missing is visualizations is dynamic vehicle sizing. The 3D vehicle models that Tesla has been using have a static size. When the vehicle sees a bus, it calculates its length, width, and height in addition to a bunch of other metrics. However, the 3D model that is shown onscreen is a predefined size, meaning that it does not actually match what the vehicle saw.
This is why you may have seen a tractor-trailer shift forward and backward or you may have seen two vehicles on top of each other. One is signifying the start of the vehicle and since the vehicle is so much longer than the model, it's adding another vehicle to the end to signify the end of the vehicle.
Scalable Vehicle Models
However, in the latest 10.10.2 FSD update, we are now seeing Tesla scale individual vehicle models so that they represent the calculated size of surrounding vehicles. Contextually this could be helpful in better understanding our car’s situation in the world.
In 10.10.2, the car shrinks or stretches the 3D vehicle models in each dimension so that the 3D model matches the calculated dimensions for each vehicle. This is especially apparent in longer vehicles such as buses, trucks, and tractor-trailers, where the vehicle lengths are more likely to vary, but you can also see it scale other vehicle models such as very small cars.
In this example below, you'll see that Tesla is now able to accurately represent buses of different sizes. Tesla only has a model for a full length bus, but in this case, Tesla detected that the length of one of the buses is considerably shorter than the vehicle model so it chose to reduce the length of the bus to the length Autopilot had calculated. In the image below you can see how the same bus model is shown in two different sizes.
Tesla can now accurate render vehicles of different sizes
It's important to realize the difference between the visualizations and what Autopilot uses. The visualizations are there merely to help us better understand what Autopilot can see. The FSD computer itself has always been taking note of the size of surrounding objects and various other data points. Trajectory, approach velocity, proximity, and so forth have also been a part of this, but this update helps Tesla achieve visualizations that provide a more accurate representation of reality.
It's not only buses and trucks that are scaled up or down. Tesla resized a bobcat down to a vehicle that is about half the length of its normal sedan model.
Tesla can now accurate render vehicles of different sizes
Models are adjusted in all three dimensions. We witnessed some truck models that were stretched to become taller while also having their length reduced. It's not perfect because you're scaling all components of the truck at the same rate, but it produces a much more accurate representation of the vehicle and the amount of space it takes up.
Vehicles are resized in three dimensions to better match the vehicle's length, width and height
Tesla has come a long way in a short period with how many objects they're able to detect, but obviously, when you compare the environment the car sees today, there is still a lot missing.
In the short term, we'd like to see more objects visualized. Objects that are commonly encountered while driving, such as trailers and gates.
We'd also like to see other common objects added, such as additional traffic light configurations, crosswalks, mailboxes, and maybe even a generic object that lets us know the vehicle sees something it needs to maneuver around, but it may not know exactly what it is.
In the future, I think we'll see Tesla display a rich, fuller 3D environment that will display static and moving objects that are important for the vehicle to avoid, objects such as barriers, buildings, trees, sidewalks, and more. Today Tesla is one step closer to achieving this goal.
The Super Manifold is Tesla’s solution to reducing the complexity of a heat pump system for an EV. Tesla showed off its engineering chops back with the original Model Y in 2019, where it introduced a new 8-way valve (the Octovalve) and a new heat pump alongside the uniquely designed Super Manifold to improve efficiency.
Now, Tesla is launching an improved version with the refreshed Model Y - the Super Manifold V2. We got to hear about it thanks to Sandy Munro’s interview with Tesla’s Lars Moravy (Vice President of Vehicle Engineering) and Franz Von Holzhausen (Chief of Vehicle Design). You can watch the video further below.
What Is The Super Manifold?
The Super Manifold (get it, Superman?), is an all-in-one package that brings in all the components of a heat pump system into one component. The Super Manifold packs all the refrigerant and coolant components around a 2-layer PCB (printed circuit board).
This Super Manifold would normally have 15 or 20 separate components, but Tesla managed to integrate them all into one nice package. That presented Tesla with a new challenge: how to integrate a heat pump—capable of both heating and cooling—into a single, efficient platform?
Several years ago, Tesla designed the Octovalve. It combines inlets and outlets and can variably change between heating or cooling on the fly - without needing to be plumbed in different directions. This is especially important for EVs, which may need to heat the battery with the waste heat generated from the motors or the heat pump while also cooling the cabin - or vice versa.
Original Super Manifold V1.1
Tesla launched the Super Manifold V1.1 back in 2022, and it provided some minor improvements to the waste heat processing of the heat exchange system. It also tightened up the Octovalve, preventing the leakage of oils into the HVAC loop that could cause it to freeze at extremely low temperatures.
Tesla has been using the V1.1 for several years now, and it has really solved the vast majority of issues with the heat pump system that many older Model Ys experienced.
Super Manifold V2 Coming Soon
Now, Tesla is introducing the Super Manifold V2 in the new Model Y. It will improve the overall cooling capacity provided by the original Super Manifold, but unfortunately, not every single new Model Y will come with it equipped. Tesla will be introducing it slowly across the lineup and at different rates at different factories, depending on part availability.
Eventually, the Super Manifold V2 will also make its way to other vehicles, potentially including the upcoming refresh for the Model S and Model X, but initially, it’ll be exclusive to the new Model Y. Tesla expects to have the new manifold in every new Model Y later this year.
If you’re interested in checking out the whole video, we’ve got it for you below.
Mark Rober, of glitter bomb package fame, recently released a video titled Can You Fool A Self-Driving Car? (posted below). Of course, the vehicle featured in the video was none other than a Tesla - but there’s a lot wrong with this video that we’d like to discuss.
We did some digging and let the last couple of days play out before making our case. Mark Rober’s Wile E. Coyote video is fatally flawed.
The Premise
Mark Rober wanted to prove whether or not it was possible to fool a self-driving vehicle, using various test scenarios. These included a wall painted to look like a road, low-lying fog, mannequins, hurricane-force rain, and bright beams.
All of these individual “tests” had their own issues - not least because Mark didn’t adhere to any sort of testing methodology, but because he was looking for a result - and edited his tests until he was sure of it.
Interestingly, many folks on X were quick to spot that Mark had been previously sponsored by Google to use a Pixel phone - but was using an iPhone to record within the vehicle - which he had edited to look like a Pixel phone for some reason. This, alongside other poor edits and cuts, led many, including us, to believe that Mark’s testing was edited and flawed.
Flaw 1: Autopilot, Not FSD
Let’s take a look at the first flaw. Mark tested Autopilot - not FSD. Autopilot is a driving aid for lane centering and speed control - and is not the least bit autonomous. It cannot take evasive maneuvers outside the lane it is in, but it can use the full stable of Tesla’s extensive features, including Automatic Emergency Braking, Forward Collision Warnings, Blind Spot Collision Warnings, and Lane Departure Avoidance.
On the other hand, FSD is allowed and capable of departing the lane to avoid a collision. That means that even if Autopilot tried to stop and was unable to, it would still impact whatever obstacle was in front of it - unlike FSD.
As we continue with the FSD argument - remember that Autopilot is running on a 5-year-old software stack that hasn’t seen updates. Sadly, this is the reality of Tesla not updating the Autopilot stack for quite some time. It seems likely that they’ll eventually bring a trimmed-down version of FSD to replace Autopilot, but that hasn’t happened yet.
Mark later admitted that he used Autopilot rather than FSD because “You cannot engage FSD without putting in a destination,” which is also incorrect. It is possible to engage FSD without a destination, but FSD chooses its own route. Where it goes isn’t within your control until you select a destination, but it tends to navigate through roads in a generally forward direction.
The whole situation, from not having FSD on the vehicle to not knowing you can activate FSD without a destination, suggests Mark is rather unfamiliar with FSD and likely has limited exposure to the feature.
Let’s keep in mind that FSD costs $99 for a single month, so there’s no excuse for him not using it in this video.
Flaw 2: Cancelling AP and Pushing Pedals
Many people on X also followed up with reports that Mark was pushing the pedals or pulling on the steering wheel. When you tap on the brake pedal or pull or jerk the steering wheel too much, Autopilot will disengage. For some reason, during each of his “tests,” Mark closely held the steering wheel of the vehicle.
This comes off as rather odd - at the extremely short distances he was enabling AP at, there wouldn’t be enough time for a wheel nag or takeover warning required. In addition, we can visibly see him pulling the steering wheel before “impact” in multiple tests.
Over on X, techAU breaks it down excellently on a per-test basis. Mark did not engage AP in several tests, and he potentially used the accelerator pedal during the first test - which means that Automatic Emergency Braking is overridden. In another test, Mark admitted to using the pedals.
Flaw 3: Luminar Sponsored
This video was potentially sponsored by a LiDAR manufacturer - Luminar. Although Mark says that this isn’t the case. Interestingly, Luminar makes LiDAR rigs for Tesla - who uses them to test ground truth accuracy for FSD. Just as interesting, Luminar’s Earnings Call was also coming up at the time of the video’s posting.
Luminar had linked the video at the top of their homepage but has since taken it down. While Mark did not admit to being sponsored by Luminar, there appear to be more distinct conflicts of interest, as Mark’s charity foundation has received donations from Luminar’s CEO.
Given the positivity of the results for Luminar, it seems that the video had been well-designed and well-timed to take advantage of the current wave of negativity against Tesla, while also driving up Luminar’s stock.
Flaw 4: Vision-based Depth Estimation
The next flaw to address is the fact that humans and machines can judge depth using vision. On X, user Abdou ran the “invisible wall” through a monocular depth estimation model (DepthAnythingV2) - one that uses a single image with a single angle. This fairly simplified model can estimate the distance and depth of items inside an image - and it was able to differentiate the fake wall from its surroundings easily.
Tesla’s FSD uses a far more advanced multi-angle, multi-image tool that stitches together and creates a 3D model of the environment around it and then analyzes the result for decision-making and prediction. Tesla’s more refined and complex model would be far more able to easily detect such an obstacle - and these innovations are far more recent than the 5-year-old Autopilot stack.
While detecting distances is more difficult in a single image, once you have multiple images, such as in a video feed, you can more easily decipher between objects and determine distances by tracking the size of each pixel as the object approaches. Essentially, if all pixels are growing at a constant rate, then that means it’s a flat object — like a wall.
Case in Point: Chinese FSD Testers
To make the case stronger - some Chinese FSD testers took to the streets and put up a semi-transparent sheet - which the vehicle refused to drive through or drive near. It would immediately attempt to maneuver away each time the test was engaged - and refused to advance with a pedestrian standing in the road.
Would FSD hit a transparent film wall? This test showed it just avoids it.
Thanks to Douyin and Aaron Li for putting this together, as it makes an excellent basic example of how FSD would handle such a situation in real life.
Flaw 5: The Follow-Up Video and Interview
Following the community backlash, Mark released a video on X, hoping to resolve the community’s concerns. However, this also backfired. It turned out Mark’s second video was of an entirely different take than the one in the original video - this was at a different speed, angle, and time of initiation.
Mark then followed up with an interview with Philip DeFranco (below), where he said that there were multiple takes and that he used Autopilot because he didn’t know that FSD could be engaged without a destination. He also answered here that Luminar supposedly did not pay him for the video - even with their big showing as the “leader in LiDAR technology” throughout the video.
Putting It All Together
Overall, Mark’s video was rather duplicitous - he recorded multiple takes to get what he needed, prevented Tesla’s software from functioning properly by intervening, and used an outdated feature set that isn’t FSD - like his video is titled.
Upcoming Videos
Several other video creators are already working to replicate what Mark “tried” to test in this video.
To get a complete picture, we need to see unedited takes, even if they’re included at the end of the video. The full vehicle specifications should also be disclosed. Additionally, the test should be conducted using Tesla’s latest hardware and software—specifically, an HW4 vehicle running FSD v13.2.8.
In Mark’s video, Autopilot was engaged just seconds before impact. However, for a proper evaluation, FSD should be activated much earlier, allowing it time to react and, if capable, stop before hitting the wall.
A wave of new videos is likely on the way—stay tuned, and we’ll be sure to cover the best ones.