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.
Subscribe
Subscribe to our newsletter to stay up to date on the latest Tesla news, upcoming features and software updates.
Your Tesla is packed with features designed to improve your comfort and safety, and Cabin Overheat Protection (COP) is a prime example. While all the materials and equipment in your car are built to withstand the summer heat, this feature prevents the interior from reaching excessively high temperatures when parked.
But what does it do, how does it work, and when should you really use it? Let’s dive in.
What is Cabin Overheat Protection?
Cabin Overheat Protection is a climate control feature that activates automatically after you’ve left your vehicle. Its primary goal is to keep the interior cabin temperature from soaring on hot days, and helping to keep the surfaces humans touch most often - like the seats, steering wheel, and screen- at a more manageable temperature.
You can also use Cabin Overheat Protection to protect temperature-sensitive items from excessive temperatures; however, its primary goal is to prevent the cabin from becoming excessively hot.
For moderate durations, Cabin Overheat Protection can actually reduce the amount of energy spent cooling your vehicle, as it’s more efficient to maintain a temperature rather than letting cooling it down from 130ºF. However, it most cases, Cabin Overheat Protection will use additional energy.
It is important to note what Cabin Overheat Protection is not. It isn’t designed to protect people or pets. For that, you’ll want to use Tesla’s dedicated “Dog Mode” or “Keep Climate On” features, which offer more robust control over the internal temperature. You can read a comparison of the major climate features here.
Enable Cabin Overheat Protection
Tesla offers several options for cabin overheat protection, allowing you to choose when and how it operates. You can enable it in your vehicle or through the Tesla app:
In the Vehicle: Navigate to Controls > Safety > Cabin Overheat Protection.
Via the Tesla App: Go to the Climate, swipe up, and toggle Cabin Overheat Protection.
Cabin Overheat Protection Settings
When enabling COP, you can pick from three settings:
Off: The system is completely disabled and will not activate when the vehicle is parked. This is the default option.
No A/C: If the interior temperature exceeds your set threshold (see below), your vehicle will only use the HVAC fan to circulate outside air through the cabin. This helps cool the vehicle since outside air is often cooler than the inside, which can easily reach 130ºF or higher. This is our recommended setting, as it helps prevent the cabin from getting too hot in most situations and uses minimal energy.
On: If the interior temperature exceeds your set threshold, the system will use both the fan and the air conditioning to actively cool the cabin down to and maintain it below that threshold. This is the most effective cooling option, but it also uses a significant amount of energy.
You can also set a Temperature Threshold for activating Cabin Overheat Protection. Tesla provides three options: 90°F (30°C), 95°F (35°C), or 100°F (40°C). Cabin Overheat Protection will attempt to maintain your vehicle at the threshold while it is active.
Battery Drain
The main reason you might choose to leave Cabin Overheat Protection off is its energy impact, which will not only increase your costs but also reduce your vehicle’s range. Ultimately, this feature keeps your vehicle’s HVAC system—or at least its fans—running to help cool the cabin.
While the No A/C mode consumes minimal energy, the On mode (which uses air conditioning) will noticeably drain the battery, particularly on hot days when the system works harder to maintain the set temperature.
The amount of energy COP uses will vary greatly based on your selected activation temperature, the exterior temperature, and whether your vehicle is parked in the sun. However, in general, the energy impact will be minimal if COP is set to No A/C, and significant if it’s set to On.
As a reminder, Cabin Overheat Protection will automatically shut off after 12 hours of operation or if the vehicle’s state of charge falls below 20%. COP and several other Tesla features will increase the cost of using your vehicle. We recently reviewed all Tesla features that continue to use power while your vehicle is parked.
Is Cabin Overheat Protection Necessary?
This is a common question, and the answer is no, Cabin Overheat Protection is not essential. Tesla vehicles, including their interior components, are designed and tested to withstand the typical automotive temperature cycles, including both hot and cold. While keeping the cabin cooler could potentially provide some marginal benefit in preventing the leather or other surfaces from degrading, the primary purpose is for the comfort of the occupants when they return.
What About Extreme Cold?
We’ve talked about heat, but what about extreme cold? Cabin Overheat Protection, as the name implies, deals with heat and will not prevent your vehicle from getting too cold. For cold weather, your Tesla has different mechanisms.
Your vehicle will automatically use energy to keep its high-voltage battery within a safe temperature range in extreme cold, whether or not you’re in the car. This helps protect the battery’s health and ensures you’ll have a minimal level of performance even if you enter the vehicle without preconditioning.
For optimal comfort in cold weather, preconditioning your vehicle will warm up the cabin and battery for improved performance.
Cabin Overheat Protection is a valuable feature that improves the comfort of your Tesla, particularly during hot weather. However, it’s not designed to improve the lifespan of your vehicle's interior, and it should not be used for people or pets (use Keep Climate or Dog Mode for those situations).
If you're parked in extreme heat and have sensitive items in the car, this could be an ideal use case. Use Keep Climate if you need to keep the items below 80°F, or Cabin Overheat Protection if you’re just looking to protect them from excessive temperatures.
Tesla’s recent focus on expanding and vertically integrating its battery production is beginning to take global steps, starting with a battery recycling and service center in South Australia. In Marion, a suburb of Adelaide, the council recently voted in favor of a proposal that would see contaminated public land developed and leased to Tesla.
The move promises local jobs and environmental remediation but has garnered a lot of public debate focused on Elon’s moves outside his role as CEO.
The proposal involves a site that’s currently unusable for recreation due to chemical contamination. A local developer plans to acquire and remediate the land, constructing a new facility specifically for Tesla. This site would reportedly serve two purposes: recycling old lithium-ion batteries and serving as a Tesla Service Center.
Tesla’s Commitment to Recycling
Tesla recently announced its intention to ramp up its battery recycling and repurposing efforts. During the Q1 2025 Earnings Call, Tesla’s executives highlighted substantial progress. Tesla had recycled enough materials in Q1 2025 to build approximately 21,000 Model Y RWD vehicles, representing a 136% year-over-year increase from Q1 2024.
Dedicated regional hubs like this one would be a logical next step in expanding the recycling loop and furthering Tesla’s vertical integration while also reducing its reliance on new materials. In addition, local sources also mentioned that Tesla could be repurposing older lithium-ion batteries for other purposes, including their inclusion in stationary battery storage systems like Powerwall or Megapack.
Of course, the facility also has major benefits for the local community, including creating around 100 local jobs, as well as injecting approximately $56 million into the local economy. Further, developing the contaminated land as a renewable facility is one of the safest ways to use the land that’s been sealed off from the public for nearly a decade.
Elon’s Image
The proposal isn’t without its critics. Local opposition was voiced during community consultations, with most of the negative sentiment directed towards Elon rather than the facility itself. Despite these complaints, the local council elected to proceed, arguing that tangible economic and environmental benefits far outweigh any perceived geopolitical or symbolic harm that shutting down the project could cause.
With the council’s endorsement on record, the proposal now moves to the South Australian state government for approvals regarding the change in land classification.
![Tesla Adds Third-Party Charge Cable Release Shortcut in Update 2025.20 [VIDEO]](https://www.notateslaapp.com/img/containers/article_images/2021/ccs-adapter.jpg/596b5f1e1d3797f6d2e2667c8af972f7/ccs-adapter.jpg)
![Andrej Karpathy considers returning to Tesla to work on Optimus [video]](https://www.notateslaapp.com/images/news/2022/karpathy-podcast_300w.jpg)
