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.
Tesla is rolling out a fairly big update for its iOS and early-access-only Robotaxi app, delivering a suite of improvements that address user feedback from the initial launch last month. The update improves the user experience with increased flexibility, more information, and overall design polish.
The most prominent feature in this update is that Tesla now allows you to adjust your pickup location. Once a Robotaxi arrives at your pickup location, you have 15 minutes to start the ride. The app will now display the remaining time your Robotaxi will wait for you, counting down from 15:00. The wait time is also shown in the iOS Live Activity if your phone is on the lock screen.
How Adjustable Pickups Work
We previously speculated that Tesla had predetermined pickup locations, as the pickup location wasn’t always where the user was. Now, with the ability to adjust the pickup location, we can clearly see that Tesla has specific locations where users can be picked up.
Rather than allowing users to drop a pin anywhere on the map, the new feature works by having the user drag the map to their desired area. The app then presents a list of nearby, predetermined locations to choose from. Once a user selects a spot from this curated list, they hit “Confirm.” The pickup site can also be changed while the vehicle is en route.
This specific implementation raises an interesting question: Why limit users to predetermined spots? The answer likely lies in how Tesla utilizes fleet data to improve its service.
Here is the new Tesla Robotaxi pickup location adjustment feature.
While the app is still only available on iOS through Apple’s TestFlight program, invited users can download and update the app.
Tesla included these release notes in update 25.7.0 of the Robotaxi app:
You can now adjust pickup location
Display the remaining wait time at pickup in the app and Live Activity
Design improvements
Bug fixes and stability improvements
Nic Cruz Patane
Why Predetermined Pick Up Spots?
The use of predetermined pickup points is less of a limitation and more of a feature. These curated locations are almost certainly spots that Tesla’s fleet data has identified as optimal and safe for an autonomous vehicle to perform a pickup or drop-off.
This suggests that Tesla is methodically “mapping” its service area not just for calibration and validation of FSD builds but also to help perform the first and last 50-foot interactions that are critical to a safe and smooth ride-hailing experience.
An optimal pickup point likely has several key characteristics identified by the fleet, including:
A safe and clear pull-away area away from traffic
Good visibility for cameras, free of obstructions
Easy entry and exit paths for an autonomous vehicle
This change to pick-up locations reveals how Tesla’s Robotaxi Network is more than just Unsupervised FSD. There are a lot of moving parts, many of which Tesla recently implemented, and others that likely still need to be implemented, such as automated charging.
Frequent Updates
This latest update delivers a much-needed feature for adjusting pickup locations, but it also gives us a view into exactly what Tesla is doing with all the data it is collecting with its validation vehicles rolling around Austin, alongside its Robotaxi fleet.
Tesla is quickly iterating on its app and presumably the vehicle’s software to build a reliable and predictable network, using data to perfect every aspect of the experience, from the moment you hail the ride to the moment you step out of the car.
The massive legislative effort titled the "Big Beautiful Bill" is taking direct aim at what has become one of Tesla’s most critical and profitable revenue streams: the sale of US regulatory credits. The bill could eliminate billions of dollars from Tesla’s bottom line each year and will slow down the transition to electric vehicles in the US.
The financial stakes for Tesla are absolutely immense. In 2024, Tesla generated $2.76 billion from selling these credits. This high-margin revenue was the sole reason Tesla posted a profit in Q1 2025; without the $595 million from regulatory credits, Tesla’s reported $409 million in profit would have been a $189 million loss.
How the ZEV Credit System Works
Zero-Emission Vehicle (ZEV) credits are part of state-level programs, led by California, designed to accelerate the adoption of electric vehicles. Each year, automakers are required to hold a certain number of ZEV credits, with the amount based on their total vehicle sales within that state. Under this system, automakers that fail to sell a certain percentage of zero-emission vehicles must either pay a significant fine or purchase credits from a company that exceeds the mandate.
Automakers who fail to sell enough EVs to meet their quota have a deficit and face two choices: pay a hefty fine to the state government for each missing credit (for example, $5,000 per credit in California) or buy credits from a company with a surplus.
As an all-EV company, Tesla generates a massive surplus of these credits. It can then turn around and sell them to legacy automakers at prices cheaper than the fine, creating a win-win scenario: the legacy automaker avoids a larger penalty, and Tesla gains a lucrative, near-pure-profit revenue stream.
This new bill will dismantle this by eliminating the financial penalties for non-compliance, which would effectively make Tesla’s credits worthless. While the ZEV program is a state law, the Big Beautiful Bill will fully eliminate the penalties at a federal level.
A Multi-Billion Dollar Impact
The removal of US ZEGV credits would be a severe blow to Tesla’s financials. One JPMorgan analyst estimated that the move could reduce Tesla’s earnings by over 50%, representing a potential annual loss of $2 billion. While Tesla also earns similar credits in Europe and China, analysts suggest that 80-90% of its credit revenue in Q1 2025 came from US programs.
Why the Program Exists
While the impact on Tesla would be direct and immediate, the credit system has a wider purpose. It creates a strong financial incentive for legacy automakers to develop and accelerate their zero-emission vehicle programs, whether it’s hydrogen, electric, or another alternative.
Eliminating the need for these credits would remove that financial pressure. This could allow traditional automakers to slow their EV transition in the US without the fear of a financial penalty, potentially leading to fewer EV choices for consumers and a slower path to vehicle electrification in the country.
Big, But Not Beautiful
On Sunday Morning TV, Elon Musk was asked his thoughts on the Big Beautiful Bill. They were pretty simple. A bill could be big, or it could be beautiful - I don’t know if it can be both, Musk stated.
Elon Musk in new interview: "I was disappointed to see the massive spending bill, frankly, which increases the budget deficit and undermines the work the DOGE team is doing. I think a bill could be big, or it could be beautiful—I don't know if it can be both." pic.twitter.com/DnyjHN7xCY
The bill poses a threat to Tesla’s bottom line and to the adoption of EVs in the US market, where automakers will no longer have a financial incentive to transition to cleaner vehicles, a market they’ve regularly struggled in when competing against Tesla.
Tesla will have to work carefully in the future to cut expenses to remain profitable after the elimination of these regulatory credits.
![Tesla Updates Robotaxi App: Adds Adjustable Pick Up Locations, Shows Wait Time and More [VIDEO]](https://www.notateslaapp.com/img/containers/article_images/tesla-app/robotaxi-app/25-7-0/robotaxi-app-25.7.0.webp/4ac9ed40be870cfcf6e851fce21c43b9/robotaxi-app-25.7.0.jpg)
