Connect with us
fsd-plaid-1 fsd-plaid-1

News

Tesla starts rolling out FSD 10.9 with “more natural” left turns and “calmer” launches

Credit: @evamcmillan333/Twitter)

Published

on

Tesla started rolling out FSD Beta 10.9. According to the release notes, V10.9 features a number of incremental changes that might provide a noticeable improvement in FSD Beta’s real-world performance. 

Based on reports online, FSD Beta 10.9 appears to be part of software update 2021.44.30.10. Noted Tesla hacker @greentheonly further remarked that the EV maker is rolling out a new map update with its recent patch. These updated maps might make the Tesla user experience better during trips. 

A look at the release notes for V10.9 suggests that Tesla is hard at work to make FSD Beta behave more and more like a human driver. Particularly interesting are references to “more natural” unprotected left turns, which should increase the system’s safety, as well as “calmer” launches when there are imminent slowdowns ahead, which should make the drive smoother than before

The following are the specific release notes for FSD Beta 10.9. 

Advertisement

Early Access Program FSD Beta 10.9 

  • Improved intersection extents and right of way assignment by updating modeling of intersection areas from dense rasters (“bag of points”) to sparse instances. Increased intersection region IOU by 4.2%. The sparse intersection network is the first model deployed with an auto-regressive architecture that runs natively with low latency on the TRIP Al accelerator chip, through innovations in the Al compiler stack. 
  • Upgraded generalized static object network to use 10-bit photon count streams rather than 8-bit ISP tonemapped images by adding 10-bit inference support in the Al compiler stack. Improved overall recall by 3.9% and precision by 1.7%. 
  • Made unprotected left turns across oncoming lanes more natural by proceeding straight into intersection while yielding, before initiating the turn. 
  • Improved lane preference and topology estimation by 1.2% with a network update and a new format for navigation clues. 
  • Improved short deadline lane changes with better modeling of necessary deceleration for maneuvers beyond the lane change. 
  • Improved future paths for objects not confined to lane geometry by better modeling of their kinematics. 
  • Made launches from stop more calm when there in an imminent slowdown nearby. 
  • Improved gap selection when yielding to a stream of oncoming cars on narrow roads. 

In recent posts on Twitter, Tesla CEO Elon Musk has stated that FSD Beta should start rolling out to Canada in the next two to four weeks, though the company plans to be “cautious.” Musk confirmed that since the FSD Beta program was launched in October 2020, there has not been one accident or injury involving the advanced driver-assist system to date. 

The Teslarati team would appreciate hearing from you. If you have any tips, reach out to me at maria@teslarati.com or via Twitter @Writer_01001101.

Maria--aka "M"-- is an experienced writer and book editor. She's written about several topics including health, tech, and politics. As a book editor, she's worked with authors who write Sci-Fi, Romance, and Dark Fantasy. M loves hearing from TESLARATI readers. If you have any tips or article ideas, contact her at maria@teslarati.com or via X, @Writer_01001101.

Advertisement
Comments

News

Tesla Model Y L gets biggest hint yet that it’s coming to the U.S.

Over the past week, a noticeable wave of American Tesla influencers descended on China and Australia, each posting in-depth YouTube reviews of the Model Y L within days of one another.

Published

on

Credit: Tesla China

The Tesla Model Y L is perhaps the most wanted vehicle in the company’s lineup in the United States, especially now that it is void of a true family vehicle with the removal of the Model X.

In China, Tesla currently offers a longer, more family-friendly version of the Model Y, known as the Model Y L, which is longer in terms of its wheelbase and larger in terms of interior space, making it the perfect option for those with a need for a tad more room than what the all-electric crossover offers in its Standard, Premium, and Performance trims.

However, there seems to be a hint that the Model Y L could be on its way to the United States. Over the past week, a noticeable wave of American Tesla influencers descended on China and Australia, each posting in-depth YouTube reviews of the Model Y L within days of one another:

The timing has sparked some intense speculation as to whether Tesla is quietly preparing to bring the long-wheelbase, three-row family SUV to North America after months of requests from fans.

The Model Y L stretches the wheelbase by about five inches compared to the standard Model Y.

Advertisement

This delivers dramatically more rear legroom, optional captain’s chairs in the second row, and a true six- or seven-seat configuration ideal for growing families. Reviewers praise its refined ride, upgraded interior features like a rear touchscreen and premium audio, and competitive range—up to roughly 466 miles in some configurations.

Many observers see the coordinated influencer trip as more than a coincidence. Tesla China appears to have hosted the group, possibly tied to the Beijing Auto Show, giving U.S.-focused creators early access to hands-on footage aimed squarely at North American audiences.

Tesla Model Y lineup expansion signals an uncomfortable reality for consumers

Tesla watchers are quick to point out this isn’t the first time such a pattern has emerged.

Advertisement

Just months earlier, American influencers were similarly invited to China to test-drive the refreshed Model Y Performance. Those videos dropped in the lead-up to the variant’s U.S. rollout, generating exactly the kind of pre-launch hype that helped smooth its September arrival in American showrooms.

The parallel is obviously hard to ignore, as Tesla has used overseas influencer trips before as a low-key way to build anticipation without formal announcements. With the Model Y L potentially hitting the U.S. market late this year, according to CEO Elon Musk, the timing would make sense.

Tesla Model Y L might not come to the U.S., and it’s a missed opportunity

Of course, it could still be coincidental. Tesla regularly invites creators to its Shanghai factory and events for broader promotional purposes, and the Model Y L has been on sale in China for some time. No official word has come from Tesla or Elon Musk about U.S. availability, pricing, or timing.

Advertisement

Import tariffs, regulatory hurdles, and production priorities at Fremont or the new Mexican Gigafactory could still delay or alter any stateside plans.

Even so, the buzz is real. U.S. families have long asked for a more spacious, three-row Tesla SUV that doesn’t require stepping up to the larger Model X.

If the influencer campaign is any indication, the Model Y L—or a close North American cousin—could finally answer that call. For now, American Tesla fans are watching closely and wondering whether this latest China trip is just good content… or the opening act for something much bigger stateside.

Advertisement
Continue Reading

News

Tesla begins probing owners on FSD’s navigation errors with small but mighty change

Previously lumped under “Other,” these incidents made it harder for Tesla’s AI team to isolate and prioritize map-related issues in their reinforcement learning models. There was a lot of disagreement on how certain interventions should be reported.

Published

on

Tesla has started probing owners on how often its Full Self-Driving suite has Navigation errors with a small but mighty change last night.

In its latest Software Update, which is Version 2026.2.9.9 featuring Full Self-Driving (Supervised) v14.3.2, Tesla has introduced a targeted improvement to how owners will report interventions.

With the initial rollout of v14.3.2, Tesla introduced a new Intervention Menu that appears when a disengagement occurs. It allowed owners to choose from four different categories: Preference, Comfort, Critical, or Other.

Tesla has voided the Other option and replaced it with a new “Navigation” choice, which seems much more ideal given the complaints owners have had about navigation. This seemingly minor UI tweak, rolled out widely in recent days, marks another step in Tesla’s ongoing effort to refine its autonomous driving stack through precise, crowdsourced data.

Advertisement

Tesla made this change in direct response to longstanding community feedback. For years, FSD users have noted that navigation errors—such as incorrect speed limits, suboptimal routes, or directing the vehicle to a building’s rear entrance instead of the main one—frequently force interventions.

Previously lumped under “Other,” these incidents made it harder for Tesla’s AI team to isolate and prioritize map-related issues in their reinforcement learning models. There was a lot of disagreement on how certain interventions should be reported:

Advertisement

By adding a dedicated “Navigation” label, the company can now tag disengagements more accurately, feeding cleaner data into its neural networks. This supports faster iteration on routing algorithms, map accuracy, and intent-aware navigation.

Advertisement

Community consensus around Tesla’s navigation system has been consistent and candid. While the end-to-end AI driving behavior in v14.x earns widespread acclaim for smoothness and safety, navigation remains FSD’s clearest Achilles’ heel.

Owners frequently cite outdated map data, failure to learn from repeated corrections, and routing decisions that feel less intuitive than Google Maps or Apple Maps. Common complaints include phantom speed-limit changes, inefficient local roads, and poor point-of-interest handling.

Tesla Summon got insanely good in FSD v14.3.2 — Navigation? Not so much

Many drivers report intervening on navigation far more often than on core driving maneuvers, with some estimating it accounts for the majority of disengagements outside of edge cases.

Advertisement

Long-term users note that the same mapping glitches persist across years and software versions, despite thousands of collective miles of feedback. Yet the addition of the “Navigation” option has been met with optimism. It signals Tesla’s commitment to data-driven progress and suggests navigation improvements could arrive sooner.

For a community that already logs millions of FSD miles monthly, this small change could unlock meaningful gains in reliability and user trust—potentially accelerating the path to unsupervised autonomy.

Continue Reading

News

Tesla expands Robotaxi in a way that was long anticipated

Instead, it has to do with the consumer base it offers Robotaxi to, because it has not offered it to everyone in the past.

Published

on

Credit: Grok Imagine

Tesla has expanded Robotaxi in a way that was long anticipated, and it does not have to do with a new, larger geofence in a city where it already offered its partially autonomous ride-hailing suite, or a new city altogether.

Instead, it has to do with the consumer base it offers Robotaxi to, because it has not offered it to everyone in the past.

Tesla has taken a major step forward in its autonomous ride-hailing ambitions with the official launch of the Tesla Robotaxi app for Android users. Released on the Google Play Store on April 24. Titled simply “Tesla Robotaxi,” the app is now available to download directly from Tesla.

This rollout fulfills a long-anticipated expansion that opens the service to hundreds of millions of Android smartphone users who were previously unable to access it on iOS alone.

The app delivers a streamlined, driverless ride experience powered by Tesla’s automated driving technology.

Advertisement

Users sign in with a Tesla Account, view the current service area map within the app, enter a destination, and receive an estimated fare and arrival time before confirming the ride. When a Model Y from the Robotaxi fleet arrives, riders confirm the license plate, enter the vehicle, fasten their seatbelt, and tap “Start Ride” on either the app or the vehicle’s touchscreen.

During the trip, passengers have access to all the same controls that iOS users do, and can adjust climate settings, seat positions, and music while tracking progress on an in-app map. The interface also allows drop-off changes or support requests if needed. After the ride, users exit, close the doors, and submit feedback.

This Android availability directly broadens the rider base for Robotaxi in its initial service areas. Unfortunately, Android users are used to being subject to delayed launches of new features available to Tesla owners.

By removing the iOS-only barrier, Tesla instantly expands the addressable market, enabling far more people to summon and use the autonomous vehicles already operating on public roads.

Advertisement

The move is a foundational requirement for scaling ride volume and gathering the real-world data needed to refine the unsupervised Full Self-Driving system that powers every trip.

For the Robotaxi program itself, the launch signals steady operational progress. It prepares the service for higher utilization rates as the fleet grows and supports the transition from limited early deployments to a more robust network.

Tesla expands Unsupervised Robotaxi service to two new cities

Tesla has indicated that users outside current service areas can sign up at the company’s website for future notifications, pointing to a deliberate, phased geographic rollout.

Advertisement

Looking ahead, the company plans to incorporate Cybercab vehicles to increase fleet capacity and efficiency while continuing to expand service territories. With the Android app now live, Tesla has removed a key adoption hurdle and positioned Robotaxi for the next phase of growth in autonomous urban transportation.

The infrastructure is now in place to support significantly larger rider demand as production and deployment accelerate.

Continue Reading