Connect with us
Tesla Autopilot in 'Shadow Mode' will pit human vs computer Tesla Autopilot in 'Shadow Mode' will pit human vs computer

News

Tesla pits human vs. computer while cars operate in ‘Shadow Mode’

Published

on

No one doubts that Elon Musk wants Tesla to be the first car company to offer fully autonomous cars to the public. After last night’s announcement that second generation Autopilot hardware, with 8 cameras and 40x more powerful computer, is now included in every car built at the Fremont factory, the question is not if Tesla will be first to market with self driving cars, but when.

As noted by white hat hacker Jason Hughes, it took a year for Tesla to activate the first version of Autopilot after the hardware was first added to production cars. New Tesla vehicles with self-driving hardware will likely see the same timeline before their vehicles become fully autonomous. But why?

Remember, Tesla has gotten some push back on its Autopilot system since Joshua Brown was killed on a Florida highway last May. German regulators recently sent a letter to all Tesla owners warning them that Autopilot is not a self-driving system and they must always pay close attention to their driving. The California DMV has proposed regulations that would prohibit Tesla or any other company from using the words “self driving” or “auto-pilot” in company literature.

Advertisement
-->

Until this point, Tesla has been free to operate Autopilot in beta mode. Regulators have deemed it to be little more than a “super cruise control” feature. But before Tesla can activate a system that purports to offer true Level 5 autonomy, it will need to convince regulators that the system functions as advertised and is safe not only for Tesla owners but for all members of the public. That is going to require data — massive amounts of data.

New Tesla Model S and Model X automobiles will run Autopilot in “shadow mode” and collect driving data that pits a human versus computer. Autopilot vehicles running in shadow mode will not take any driving-assist or self-driving actions. Rather they will only log instances when Autopilot would have taken action and compare those results to the real life actions taken by human drivers. Musk told the press that the ultimate goal is to improve its self-driving algorithms until they are better than human drivers. By having statistical data to back up the safety of its self-driving model, Tesla will have a better chance of proving to regulators that its vision for a Tesla-powered autonomous future will be safer for humanity.

However, experts in the field of autonomous driving say billions of miles of driving will be needed to verify the validity and safety of self-driving systems. Tesla now has collected approximately 220 million miles worth of data collected from Autopilot-equipped vehicles. As Tesla wirelessly adds millions more miles of driving data collected through previous generation and new ‘Enhanced Autopilot’ enabled vehicles, the company will take a commanding lead over the rest of the automotive and transportation services industry that is just beginning to understand what the future will look like.

For Tesla owners whose cars are manufactured on or after October 19, 2016 — which will include all Model 3 sedans — they will have the satisfaction of knowing their car is capable, as Elon suggests, of driving from Los Angeles to New York City without any input from the driver, then navigating New York traffic, finding a parking spot, and parking itself all without input from a human driver. It couldn’t be a better time to be a Tesla owner, especially if you care about shaping the inevitable future.

Advertisement
-->

"I write about technology and the coming zero emissions revolution."

Advertisement
Comments

News

Tesla FSD (Supervised) is about to go on “widespread” release

In a comment last October, Elon Musk stated that FSD V14.2 is “for widespread use.”

Published

on

Tesla has begun rolling out Full Self-Driving (Supervised) V14.2, and with this, the wide release of the system could very well begin. 

The update introduces a new high-resolution vision encoder, expanded emergency-vehicle handling, smarter routing, new parking options, and more refined driving behavior, among other improvements.

FSD V14.2 improvements

FSD (Supervised) V14.2’s release notes highlight a fully upgraded neural-network vision encoder capable of reading higher-resolution features, giving the system improved awareness of emergency vehicles, road obstacles, and even human gestures. Tesla also expanded its emergency-vehicle protocols, adding controlled pull-overs and yielding behavior for police cars, fire trucks, and ambulances, among others.

A deeper integration of navigation and routing into the vision network now allows the system to respond to blocked roads or detours in real time. The update also enhances decision-making in several complex scenarios, including unprotected turns, lane changes, vehicle cut-ins, and interactions with school buses. All in all, these improvements should help FSD (Supervised) V14.2 perform in a very smooth and comfortable manner.

Elon Musk’s predicted wide release

The significance of V14.2 grows when paired with Elon Musk’s comments from October. While responding to FSD tester AI DRIVR, who praised V14.1.2 for fixing “95% of indecisive lane changes and braking” and who noted that it was time for FSD to go on wide release, Musk stated that “14.2 for widespread use.”

FSD V14 has so far received a substantial amount of positive reviews from Tesla owners, many of whom have stated that the system now drives better than some human drivers as it is confident, cautious, and considerate at the same time. With V14.2 now rolling out, it remains to be seen if the update also makes it to the company’s wide FSD fleet, which is still populated by a large number of HW3 vehicles. 

Advertisement
-->
Continue Reading

News

Tesla FSD V14.2 starts rolling out to initial batch of vehicles

It would likely only be a matter of time before FSD V14.2 videos are posted and shared on social media.

Published

on

Credit: Grok Imagine

Tesla has begun pushing Full Self-Driving (Supervised) v14.2 to its initial batch of vehicles. The update was initially observed by Tesla owners and veteran FSD users on social media platform X on Friday.

So far, reports of the update have been shared by Model Y owners in California whose vehicles are equipped with the company’s AI4 hardware, though it would not be surprising if more Tesla owners across the country receive the update as well. 

Based on the release notes of the update, key improvements in FSD V14.2 include a revamped neural network for better detection of emergency vehicles, obstacles, and human gestures, as well as options to select arrival spots. 

It would likely only be a matter of time before FSD V14.2 videos are posted and shared on social media.

Following are the release notes of FSD (Supervised) V14.2, as shared on X by longtime FSD tester Whole Mars Catalog.

Advertisement
-->

Release Notes

2025.38.9.5

Currently Installed

FSD (Supervised) v14.2

Full Self-Driving (Supervised) v14.2 includes:

  • Upgraded the neural network vision encoder, leveraging higher resolution features to further improve scenarios like handling emergency vehicles, obstacles on the road, and human gestures.
  • Added Arrival Options for you to select where FSD should park: in a Parking Lot, on the Street, in a Driveway, in a Parking Garage, or at the Curbside.
  • Added handling to pull over or yield for emergency vehicles (e.g. police cars, fire trucks, ambulances.
  • Added navigation and routing into the vision-based neural network for real-time handling of blocked roads and detours.
  • Added additional Speed Profile to further customize driving style preference.
  • Improved handling for static and dynamic gates.
  • Improved offsetting for road debris (e.g. tires, tree branches, boxes).
  • Improve handling of several scenarios including: unprotected turns, lane changes, vehicle cut-ins, and school busses.
  • Improved FSD’s ability to manage system faults and improve scenarios like handling emergency vehicles, obstacles on the road, and human gestures.
  • Added Arrival Options for you to select where FSD should park: in a Parking Lot, on the Street, in a Driveway, in a Parking Garage, or at the Curbside.
  • Added handling to pull over or yield for emergency vehicles (e.g. police cars, fire trucks, ambulances).
  • Added navigation and routing into the vision-based neural network for real-time handling of blocked roads and detours.
  • Added additional Speed Profile to further customize driving style preference.
  • Improved handling for static and dynamic gates.
  • Improved offsetting for road debris (e.g. tires, tree branches, boxes).
  • Improve handling of several scenarios, including unprotected turns, lane changes, vehicle cut-ins, and school buses.
  • Improved FSD’s ability to manage system faults and recover smoothly from degraded operation for enhanced reliability.
  • Added alerting for residue build-up on interior windshield that may impact front camera visibility. If affected, visit Service for cleaning!

Upcoming Improvements:

  • Overall smoothness and sentience
  • Parking spot selection and parking quality
Continue Reading

News

Tesla Model X lost 400 pounds thanks to these changes

Published

on

Credit: Tesla

The Tesla Model X has always been one of the company’s most loved vehicles, despite its low sales figures, which can be attributed to its high price tag.

However, the Model X has been a signature item on Tesla’s menu of cars, most notably recognized by its Falcon Wing Doors, which are aware of its surroundings and open according to what’s around it.

But recent improvements to the Model X were looking slim to none, but it appears most of the fixes actually happened under the body, at least according to Tesla’s Vice President of Powertrain, Lars Moravy.

In a recent interview with Car and Driver, Moravy detailed all of the changes to the 2026 iteration of the vehicle, which was about 400 pounds lighter than it was originally. The biggest change is a modification with the rear motor, switching from an induction-type motor to a permanent-magnet design and optimizing the half-shafts, which shed about 100 pounds.

Tesla also got “almost 80 pounds out of the interior bits and pieces,” which “included making parts thinner, different manufacturing process choices, and incorporating airbag-deployment requirements into the headliner fabric,” the report said.

Additionally, the standard five-passenger, bench seat configuration saved 50 pounds by ditching pedestal mounting. This also helped with practicality, as it helped the seat fold flat. Engineers at Tesla also saved 44 pounds from the high-voltage wiring through optimizing the wiring from the charge-port DC/DC converter and switching from copper to aluminum wiring.

Tesla makes a decision on the future of its flagship Model S and Model X

Tesla also simplified the cooling system by reducing the number of radiators. It also incorporated Nürburgring cooling requirements for the Plaid variant, which saved nearly 30 pounds.

Many Tesla fans will be familiar with the megacastings, manufactured in-house by presses from IDRA, which also saves more than 20 pounds and boosts torsional stiffness by around 10 percent. Tweaks to the suspension also saved 10 pounds.

People were truly disappointed with what Tesla did with the Model S and Model X, arguing that the cars needed a more severe exterior overhaul, which might be true. However, Tesla really did a lot to reduce the weight of the vehicle, which helps increase range and efficiency. According to Grok, every 200 pounds removed adds between 7 and 15 percent to range estimations.

This makes sense considering the range estimations both increased by 7 percent from the Model X’s 2025 configuration to the 2026 builds. Range increased on the All-Wheel-Drive trim from 329 miles to 352 miles, while the Plaid went from 314 miles to 335 miles.

Continue Reading