Last week, Mark Rober, an engineering YouTuber best known for his glitter bombs, released a video where he tested Tesla's Autopilot against various conditions - including the iconic ACME painted wall.
During this test, many people noted that Mark was using Autopilot rather than FSD, even though his video was titled “Can you Fool a Self-Driving Car?”. The Tesla on Autopilot went up against a vehicle equipped with Luminar’s LIDAR rig, running some sort of basic autonomy or safety software.
New Video Tests FSD
Many people were disappointed with Mark’s video and his testing methods, so several creators got to work to actually test out Tesla’s FSD.
Creator Kyle Paul over on X made a much better follow-up video, using both a HW3 Model Y as well as an AI4 Cybertruck. In a relatively unsurprising turn of events, the Cybertruck was successfully able to detect the wall, slowed down, and came to a stop. The Cybertruck was running FSD 13.2.8.
Kyle’s team did a fantastic job building the wall and testing this in a private area using FSD rather than Autopilot. On top of that - they re-tested the results several times and recorded the entire thing in and out. While Mark’s video was more for entertainment, Kyle really set out to prove what would really happen in this unlikely scenario.
Sadly, the HW3 Model Y was unable to detect the wall, and manual intervention was required in each test. While the Model Y was running FSD 12.5.4.2 rather than an FSD V12.6 build, we don’t expect this to have had a significant impact on the test - this is more of an issue with how computer vision analyzes the environment.
There are several major differences between HW3 and HW4. The first is obviously that the version that runs on AI4 is more advanced, as the hardware is capable of processing a lot more data. However, AI4 also features much higher-resolution cameras than HW3, and Tesla recently added the ability for the video feeds to be processed at full resolution on FSD V13. This could have made the difference, although it’s not entirely clear. Perhaps if HW3 gets a version of FSD V13 in the future, HW3 can be retested to see if it passes the “ACME wall” test.
Watch
Kyle’s entire video is below. It’s only 10 minutes long, so definitely give it a watch. Props to Kyle on the quick and thorough execution.
What Does This Mean for FSD?
We broke down Mark’s test - and examined all the little issues that we discovered after doing some in-depth research - you can read our analysis here.
Putting aside the issues with Mark’s testing and instead using the new results - it seems that if you were to have to fight against Wile-E-Coyote and his ACME tools with your Tesla, cartoon logic may win if you’re on an HW3 vehicle. If you’re on an AI4 vehicle, you’ll likely come to a safe stop.
Vehicle depth perception is definitely something that Tesla has been hard at work to improve - and some fairly drastic improvements came with FSD V13 that haven’t been entirely translated to FSD V12 just yet. Future versions of HW3 FSD may be able to determine that the wall is there successfully. So Kyle - if you’re reading this - don’t get rid of that wall. We’d love to see more testing in the future.
However, this entire test scenario is so out of left field… there is a good likelihood this same test would fool some human drivers as well. The most important part is that the future of autonomy will not fall for these tricks, so it's very unlikely for someone to weaponize this idea as it’d only possibly work on a small segment of vehicles.
If Wile-E-Coyote is after you, someone else may drive into the wall before your Tesla does.
Not a Tesla App
We’re not kidding, this really happened already. This isn’t a realistic scenario outside of someone trying to play an insane prank - but it’s good to know that FSD V13 is capable of dodging this.
Subscribe
Subscribe to our newsletter to stay up to date on the latest Tesla news, upcoming features and software updates.
Tesla has finally released their 2024 Impact Report, and it's filled with impressive new data on the company’s environmental and safety progress. However, the biggest news is the clear and concrete roadmap it provides for the next generation of Tesla products.
For the first time, the report provides specific timelines for Tesla to begin volume production of the purpose-built Cybercab and the ramp-up of the Semi factory. This year’s report shifts from documenting past achievements to defining Tesla’s next phase, with a focus on autonomy and industrial transport.
Upcoming Vehicles
The most significant new items in the report are timelines for Tesla’s anticipated future vehicles.
Next, Tesla is ramping up production of the Semi, following the completion of limited production runs used for testing. This development is closely tied to the ongoing construction of the new Semi Factory, which is nearing completion. Tesla expects this to be one of its largest markets going forward and one of the most impactful. Industrial trucks doing the last 200 miles of delivery account for 16.4% of US vehicle emissions, despite making up only 1.1% of vehicles on the road.
In terms of the Affordable Model, Tesla has mentioned that they intend to launch more affordable products in 2025 and address a key segment of the market. They did not elaborate on this further and seem to have missed the previously provided self-imposed deadline for the first half of 2025.
At this point, we’re unsure whether Tesla will actually launch a distinct and more affordable model or whether it will introduce cut-down versions of the Model Y, as rumored.
Safety
The report supports Tesla’s future plans with some impressive new data points that demonstrate the impact their technology is having.
First, Autopilot (and FSD) has achieved a safety record nearly 10 times higher than the US national average in terms of miles per incident. The data shows one accident for every 6.77 million miles driven with Autopilot (or FSD) engaged, compared to the national average of one accident per 0.70 million miles.
The report also highlighted the Cybertruck’s recent 5-Star overall safety rating from the NHTSA, marking it one of the safest vehicles on the market, especially for a truck. The best part is that Cybertruck holds the lowest overall probability of injury and the lowest rollover risk of any pickup truck ever tested by the agency. Skeptics have always complained about lacking crumple zones, but the results prove otherwise, with Tesla building crumple zones as part of the gigacast.
Sustainability
In terms of sustainability, Tesla’s growing fleet helped to increase the amount of reduced and avoided emissions by 60% year over year, to 32 million metric tons of CO2e. While that’s a small number when you compare it to a full country, it is still a significant impact, especially in cities where pollutants have already decreased due to the ownership of EVs.
Tesla also mentioned that 99% of their recalls reported in 2024 were resolved using OTA updates, saving owners a trip to the Service Center or a trip by the Tesla Mobile Rangers, all in the name of sustainability and reduced costs.
Impactful Report
Tesla’s 2024 Impact Report is actually one of the most forward-looking publications to date. It puts a clear roadmap of Tesla’s future goals, while also tying them into the sustainability and safety goals achieved last year.
We can’t wait till 2025’s report - because it’ll be even better with this year’s deployment of Robotaxi. You can read all 200+ pages of the impact report here.
Tesla has officially begun internal testing of its awaited virtual queueing system for Superchargers. The news was shared by Tesla’s Director of Charging, Max de Zegher on X.
The Tesla Charging team has begun pressure testing the new feature and is planning for public pilots as their next step. While most users won’t experience heavy congestion at Superchargers, for those who do, it could be a real pain point. Virtual queues are designed to make it easier to charge at congested Superchargers by having a digital queue, rather than relying on owners to remain in line with their vehicles.
Virtual Queues
When we originally delved into Tesla’s plans to introduce a virtual queue system, it seemed obvious that the virtual queue would replace the current “Wild West” first-come, first-served system of vehicles trying to get pulled into a stall. This process will likely have two key integrations.
First up is integration directly into the vehicle software for Tesla vehicles. This means that when you’re navigating to a Supercharger that’s busy and virtual queuing is enabled, you will be automatically placed into the virtual queue upon arrival.
Then, your position in line is displayed on-screen and provides an estimated wait time, allowing you to relax, eat, or take a bathroom break without worrying about your place in line. Finally, once a stall becomes available and it’s your turn, you will receive a notification on your vehicle’s screen, as well as on the Tesla app, directing you to the open stall that will presumably only allow your vehicle to charge. We imagine that there will be a grace period for owners to pull up with their car. If that doesn’t happen within a certain period, the next car will likely be offered the charger.
The second integration is in the Tesla app for non-Tesla drivers. As Tesla continues to install Magic Docks and open Superchargers to non-Tesla EVs, more and more traffic comes to the world’s most reliable fast charging network. That means that Tesla also needs to manage expectations and queue times for non-Tesla vehicles, likely through a similar process, but done over the Tesla app instead.
The Devil’s in the Details
A simple “first-in, first-out” queue sounds great, but Max noted that it is easy to exploit things with bad actors. What prevents a driver from joining a queue remotely to reserve a spot, ignoring a notification, or trying to hop into an unreserved spot?
Well, Tesla should be able to manage these fairly easily, but they still require technical effort to implement. That means GPS geofencing for those attempting to join a queue, a short countdown timer for those late to take their spot, and a lockout for those who try to skip the queue are all needed.
What’s Next?
As Tesla has just started internal testing of this feature, it likely means that public-facing user interfaces and flows aren’t quite ready yet, but the underlying functionality is. It also means that Tesla is working to refine the little details to make the process as smooth and as easily accessible as possible.
While no pilot locations have been announced yet, it seems likely that Tesla will launch the pilot at some of the most notoriously busy Supercharger sites to gather testing data in the near future, once internal testing is complete. That means holiday travel routes or major highways, likely in California first, before rolling out elsewhere.
Virtual Queuing is a fantastic tech-first solution for the Supercharger network that helps transform that experience into a more calm and orderly process. Additionally, establishing a fair system that allows both Tesla and non-Tesla EVs to access will likely improve the overall experience. Along with the pilot program for dynamic Supercharger pricing that incentivizes people to use less-congested Superchargers, these changes should improve the Supercharger experience.
While Max mentioned it was designed for “those rare cases with a wait”, that tends to be the experience in larger cities further North, especially in New York, Michigan, or within Canada, where the few smaller Supercharger sites in big cities tend to be heavily congested. These queues will make the experience smoother for everyone involved, so we’re looking forward to seeing this come to fruition.
![Tesla Autonomously Delivers Its First Vehicle to Customer — And It’s More Impressive Than Expected [VIDEO]](https://www.notateslaapp.com/img/containers/article_images/model-y-2025/newmodely_77.jpg/382e0312c769d0bb2e1234f7ac556fad/newmodely_77.jpg)
