Tesla Earnings Call

 Tesla Earnings Call

I was talking to Mark yesterday, about the CyberTruck, and his superb YouTube channel, and he mentioned he had just finished up his 2024 Tesla Earnings video which can be see below, and he makes many superb points. Mark has a great Tesla YouTube channel named, Mark of the CyberBeast, which I highly recommend. Mark is really smart, and we talked about perhaps collaborating in the future on an article and video comparing the AWD CyberTruck to The Tri-Motor Beast CyberTruck!

Masterclass on Tesla Stock

 

Masterclass on Tesla Stock

As A Long-Term Investment Vehicle 

This interview which feature Cern Basher on Brighter with Herbert is one of the most profound conversations on the subject of the long-term value proposition of Tesla stock as an investment vehicle. In my persons option, I have long believed Tesla has had the entire automotive industry in check-mate, and will go on to become the single most valuable company on earth—by a long shot. If you study the history of Tesla stock you will discover that from its IPO on June 29, 2010 It's up 30,486.02% as of this writing. 

It is also a fact that to date, over the past decade and a half since Tesla IPO'd, it has appreciated close to 5% per month. That's 5% per month, not per year, so that means on average Tesla stock has gone up on average close to 60% per year. This is the most critical key ingredient to thrust Tesla stock up above all other companies as Tesla has magnificent trajectory, which is key.

New 2025 Tesla Model Y Launched in China

 

New 2025 Tesla Model Y 

Launched in China

Tesla finally launched the new 2025 Model Y (Codenamed Juniper) exclusively in China today, and it looks PRETTY RAD!!! It's obviously just a matter of time before the U.S. and Berlin made Model Y are updated to match this design language. I think Tesla did a GREAT job with overhauling the design of what is currently the Number 1 best selling car on earth, and yes, I am talking about the Tesla Model Y. Tesla basically just made it look way more attractive, sporty and sleek.

Exterior Updates

As we see from the image below, the Model Y "Juniper" refresh design language is similar to the upcoming Tesla RoboCab, and on the back of the vehicle we see it has a similar diffused lightbar, which looks really cool...

The new Model Y has a much sharper, cleaner vibe, as the front bumper facia, is sleeker and less bulbous, and the Duckbill/Porpoise/Botox lip look face is gone, as the new lightbar and headlights give it a much more modern persona. Also, it's slightly more aerodynamic overall, and the car is also just a big longer by 47 mm. The new Model Y Juniper measures 4797 mm in length, while its predecessor was 4750 mm long.

Matte Maroon Red with TMaxx PPF and 22" CT7 Fully Forged Wheels in Black by TSPortline

Matte Maroon Red with TMaxx PPF 
and 22" CT7 Fully Forged Wheels in Black
by TSPortline

If I could as Elon Musk One Question?

If I could as Elon Musk One Question? 

They say there is no such thing as a stupid question and If I could ask Elon Musk one question, it would be:

"How in the future will Tesla vehicles be able to drive safely using full unsupervised autonomy using just cameras? How for instance could a Tesla vehicle navigate safely on a road at night with really thick fog?"

Over the years, there has been a lot of speculation about the validity of Elon Musk's vision to make Tesla automobiles that are genuinely autonomous—meaning cars that can drive themselves without any human supervision. I have spoken to so many people who say Elon's vision is an impossible pipe dream. 

I have NEVER doubted Elon's vision, but there were two important variables I questioned.

The dream of autonomous transportation, as it was originally put forth, was to have a Tesla vehicle that could drive itself from San Francisco to New York, without a person in the vehicle. 

When Tesla first introduced FSD (Full Self Driving), there were two questions that would not stop popping into my head.

The first question, which I considered was "If a Tesla was going to be able to drive itself from San Francisco to New York, by itself, how would it charge itself along the way? 9 years ago, Tesla showed off this bizarre video that shows a prototype snake charger, that could robotically charge a Tesla through the standard wall charger outlet:

I always thought the solution above was NOT realistic or viable, but at the time I was already aware of wireless charing solutions for Electric Vehicles as I had attended the CES show in Las Vegas, and saw a working prototype that was similar to a wireless charger for a smartphone.

Back in 2020 I wrote a seminal article titled "Thoughts on the Future of Autonomous Vehicles: The Shape of Things To Come", in which I discussed my ideas on the future of autonomous vehicles. In that article, I included a profound video that showcased and documented the future reality of wireless EV charing becoming standard for autonomous cars, which can be seen below:

Recently, when Tesla announced the CyberCab, they mentioned they were going to be incorporating wireless charging, and thus one of the two final puzzle pieces was put in place. Below is an official Tesla Video that shows how their CyberCab will use wireless charging:

Of course, I realized this years ago, which was further confirmed with the advent of the CyberTruck as Sandy Munro's CyberTruck teardown discovered wire harnessing already built-in to the CyberTruck, that could simply come to life if a Tesla wireless charing pad was installed. In other words, all CyberTrucks can easily be upgraded to have wireless charging. 

So this solves half the equation. Also, it's easy to see the amazing benefits of wireless charing for Tesla vehicles. For instance, your Tesla could pull itself into your garage automatically and position itself perfectly over the wireless charing pad. Also, if you plug in a current Tesla model to charge it today at home or at a Tesla Supercharger, or at a third party charger, in order to drive away, you have to manually unplug, and thus untether the vehicle, which oftentimes can be a pain. 

With wireless charing, the drivers simply puts the car in drive and drives off. At Tesla Superchargers, it's kind of scary for many people to know they can't just drive off when they are plugged in, so if for instance somebody tried to attack them, they couldn't just drive away, without having to first get out their vehicle and manually unplug it. With wireless charing this is no longer an issue or concern.

I have even seen prototypes where the base/floor charing pad was on wheels that could move horizontally, vertically, or diagonally so it could optimize its charing position every time. Jordan Giesige, from The Limiting Factor just came out with a deep dive video on how Tesla Wireless Charing will work, which is interesting:

How "Tesla AI Vision" Works

The second half of the equation I set out to resolve, is based on the Tesla exterior camera system, which the car used to drive when placed in full self driving mode, which as of today is only available in supervised mode.

In other words, Tesla and Elon Musk have promised that in the future, they plan to release Full Self Driving (Supervised), which will allow Tesla models to drive themselves.

Several years ago, all Tesla models had both cameras and lidar sensors for autonomous driving. The logic was that whatever the camera couldn't see, the lidar could detect. Lidar is a form of radar, that can see through things.

An edge case or corner case complex driving challenge example would be:

What if an autonomous Tesla was driving itself on a slippery road where snow was falling, and there was thick fog, and let's say there was a person crossing the road, or traffic stopped ahead of your, that you could not see since the fog is so thick. If the car was traveling at 60MPH, and the cameras could not see through the fog, the lidar would see what was behind the fog, which makes perfect sense.

Vision Based Approach

But then a few years ago, Elon Musk informed the world that Tesla was completely removing lidar and all forms of radar from Tesla vehicles, and planned to move forward with a camera only approach. This confused me to no end, and with my scenario, I couldn't understand how a Tesla could drive itself safely in such a scenario as I just mentioned with all the fog, without crashing or posing a significant safety hazard.

I kept doing research on this subject and asked a number of smart people and nobody seemed to know the answer, but I recently stumbled into a video that addressed and seems to have resolved this issue. The video below is from BestINTesla and is titled: "The GPU Giants Bet Big on xAI - The Dawn of a New Era in Energy Storage - Tesla Triumphs Over Unions". In this video, around 9:44:00 he discusses this topic in detail:

In the video above he points out that Chinese EV manufacturer, Li Auto CEO voiced his concern about Tesla's camera only approach. 

Ironically, Li Auto CEO's scenario was similar to mine, but according to the video the way the Tesla cameras work, is they can use all the visible light, including in the infrared spectrum, which we as humans can't see or detect with our eyes, and can see individual photons, which serve as solution of measurement similar to lidar. This still sounds a little far fetched to me, but I plan to investigate more and once I figure out more, I will update this article.

So there you have it. If I could ask Elon Musk only one question, this would defiantly be it. One thing that still confuses me and seems to contradict this notion or solution, is why do I get FSD pop ups that say FSD is degraded due to poor weather conditions? In other words, if I drive in rain, often times Tesla TSD will either refuse to turn on altogether, and give me a message that says something like "FSD not available at this time. Please try again later", or it will turn on the FSD, and put up a message on the Tesla screen that says something like, "FSD quality is currently degraded at this time, so please pay extra close attention".

Direct Photon Counting

Update on April 22, 2025: On todays earnings call, an analyst from Wells Fargo asks a similar question, where he said people were concerned sun glare, fog and dust would blind the camera so how could Full Self Driving work under such conditions? Elon responded by saying it has to do by using Direct Photon Count.

Elon said that a typical solution assumes you use a Direct silicon photon counter, that goes through a digital image signal processor that will result in a washed out image. Elon said the challenge is that during that post processing the Digital Image Processor washes things out and creates way too much noise. 

Elon said:

"(Tesla) Had quite a big breakthrough we made a some time ago was to go with direct photon counting and bypass the image signal processor. You can drive straight toward the sun, and see in what appears to be the blackest of night. Here in fog we can see as well as people can, or slightly better."

What is Direct Photon Counting?

Direct photon counting refers to a method of capturing light at the sensor level by directly measuring individual photons (the fundamental particles of light) rather than relying on traditional image sensors that convert light into analog signals, which are then processed through a digital image signal processor (ISP). Traditional camera systems, like those used in most automotive and consumer applications, typically follow these steps:

• Light Capture: Photons hit the sensor, generating an electrical charge proportional to the light intensity.

• Analog-to-Digital Conversion: The charge is converted into an analog signal, which is then digitized.

• ISP Processing: The digital signal is processed by an ISP, which applies algorithms for noise reduction, color correction, white balance, and other enhancements to produce a usable image.

However, this traditional pipeline introduces several challenges:

• Noise: ISPs can amplify noise, especially in low-light conditions or high-contrast scenarios like sun glare, leading to washed-out or unclear images.

• Dynamic Range Limitations: Traditional sensors struggle to capture details in both very bright and very dark areas simultaneously, which is critical for driving in conditions like fog, dust, or direct sunlight.

• Latency: The processing steps add computational overhead, which can introduce delays—problematic for real-time applications like autonomous driving.

Direct photon counting, as described by Musk, bypasses much of this pipeline. Instead, it involves sensors that count individual photons directly, producing a raw, high-fidelity representation of the light entering the camera. This raw data is then fed into Tesla’s neural networks for processing, avoiding the noise and artifacts introduced by traditional ISP post-processing.

Conclusion

As I was doing more research, I asked Grok 3 the following question:

"How in the future will Tesla vehicles be able to drive safely using full unsupervised autonomy using just cameras? How for instance could a Tesla vehicle navigate safely on a road at night with really thick fog?"

I was shocked to discover that Elon quietly added radar back into Hardware 4!?!! Below was Grok 3's answer to my question:

In the future, Tesla’s camera-based FSD will enable unsupervised autonomy by advancing photon-counting cameras, neural networks, compute power, and HD maps, with HW4’s radar providing fog-penetrating redundancy. In thick fog at night, cameras could outperform human vision, using infrared and AI to navigate at 5–20 mph safely, supplemented by radar and maps. High speeds (75 mph) in such conditions are unlikely due to safety and physics, with Tesla prioritizing caution or rerouting. 

TMAXX Shamrock Greet Matte PPF

Telsa Model X Plaid

TMAXX Shamrock Greet Matte PPF

I really like this brand new PPF color from TMAXX, which TSportline wrapped this Model X Plaid with!!! I remember a friend of mine, back in the late 1990s or early 2000s drove a BMW 7 series that had a really similar shade of forest green that was so beautiful, but it was not matte like this new PPF, which gives it a frosty cool look.