Connect with us

Tesla

Tesla FSD improvements in China continues with Baidu’s help

Tesla is working with Baidu to improve FSD in China, as strict data laws prevent Tesla from training its AI locally.

Published

on

Credit: Tesla China/Weibo

Baidu is helping Tesla Full Self-Driving (FSD) improve in China.

Engineers from Baidu, a leading AI company in China, are helping Tesla with its FSD Version 13 software.

According to Reuters’ sources, Baidu recently dispatched engineers from its mapping team to Tesla’s Beijing office. The engineers are working on integrating Baidu’s navigation map information with Tesla’s FSD V13 software.

Tesla’s way of improving FSD V13 in China differs from the methods used in the United States. In the U.S., Tesla trains FSD to improve navigation techniques and learn about roads. In contrast, Tesla cannot train FSD in China due to the country’s data laws.

“Then China, which is a gigantic market, we do have some challenges because they currently don’t allow us to transfer training videos outside of China. And then the US government won’t let us do training in China. So, we’re in a bit of a there. It’s like a quandary,” noted Elon Musk during the last earnings call.

“So, we were solving then is by literally looking at videos of streets in China that are available on the Internet to understand and then feeding that into our training so that publicly available video of street signs and traffic rules in China can be used for training and then also putting it in a very accurate simulator. And so, it will train using SIM for bus lanes in China,” he added.

Advertisement
-
-

Tesla has rolled out FSD (Supervised) in Mexico and started the process to release it in parts of Europe. Despite a few regulatory issues, Musk is optimistic that FSD (Unsupervised) will be available in more countries this year.

“But I think we’ll have unsupervised FSD in almost every market this year, limited simply by regulatory issues, not technical capability. And then unsupervised FSD in the U.S. this year, in many cities but nationwide next year. And hopefully, we have unsupervised FSD in most countries by the end of next year,” he noted during the Q4 and Full Year 2024 earnings call.

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 Full Self-Driving v14.3.6 review: a rare regression, but some bright spots

Published

on

Credit: Tesla

Tesla released Full Self-Driving version 14.3.6 last week, and after what was potentially one of the best FSD releases in v14.3.5, there has been a bit of a regression. While there are some bright spots, the changes made to v14.3.6 seem to have backtracked some behaviors.

Overall, it is hard to really complain about FSD in any sense; it has revolutionized how I travel literally anywhere. According to my self-driving app, the last time I went a day without using it was 59 days ago.

However, I think it’s also important to recognize when things are just plain bad with FSD. There are times it does truly mind-boggling things, and I’ll dive into those here. Additionally, I only had these issues on local roads, not on highways. Highway operation, generally, is always incredible other than the occasional complaint about speed or left lane camping.

With those things being said, my personal experience may not represent others’ experiences. A handful of people have said they have had a similar experience on v14.3.6, while others have said it is more than normal.

Turning Hesitancy, Inaccuracy

I’ve noticed more inaccuracy turning into multi-lane stretches of road than in any version I can remember. I’ve had at least three instances of FSD turning into a stretch of roadway that has two or more lanes, and not selecting a lane confidently as it has in past versions.

Instead, the car will drive over one of the dashed road lines, and the steering wheel will jerk back and forth before picking the lane. It should be said that it has always picked the correct lane when choosing based on the navigation, but it is still very indecisive. The steering wheel jerking is reminiscent of some of the later versions of v13.

I admit I really hate to see the steering wheel jerking come back. However, I think when Tesla releases v14.3.7, it won’t be present. When there are occurrences of it in FSD versions, it is usually resolved by the following release.

FSD Disregards Manual Turn Signals

This is my biggest bone to pick with FSD other than Navigation issues, but this one seems like it would be such an easy fix.

If Tesla is going to put the word “Supervised” on the end of “Full Self-Driving,” then when I tell the car to do something, it should do it. If I input an increase in speed by pressing the accelerator, the car will immediately respond. It does not disregard my input because it feels it is traveling at the right speed.

FSD should never disobey and turn off turn signals that the driver inputs. Trying to direct the car into the correct lane, I had initiated the left turn signal not once, not twice, but three times, with the car turning it off all three times and continuing in a lane that would end in just one block. The only solution at this point would be to zipper merge.

This goes back to the fact that self-driving’s biggest bottleneck might be rider preference. A zipper merge might have been more than reasonable, might have saved me time that I spent sitting through an additional light cycle, and might be something many drivers would do. I was in no hurry, I traditionally do not try to zipper merge because it feels inconsiderate, and lastly, the car should have just followed my input.

This caused me to disengage and drive manually the rest of the way home. Sometimes I just do not need FSD to try to pass every car it can at intersections.

Bird Braking is a Thing of the Past

The big complaint with recent versions of Full Self-Driving has been what we’ve coined as “bird braking,” which is when the car will brake suddenly as a bird flies past.

There have been zero issues with this so far in v14.3.6, which is an excellent improvement.

FSD Might Already Be Taking Note of Driver Preferences

Another thing I have noticed over the past few days is that v14.3.6 seems to already be taking my preferences with navigation into account.

This is something that is supposed to be rolling out with the Summer Update, but I have a hunch it’s already present and might have been included in this v14.3.6 build. On Friday, FSD pulled into an entrance to a local convenience store that it had never attempted to go into before.

Typically, I manually pull into this entrance because it avoids heavy cross traffic at the main entrance. FSD has always chosen that congested main entrance.

Additionally, FSD has pulled into my assigned parking spot at my townhouse community on multiple occasions with this release. This is something that used to happen ocassionally, but not consistently.

It also navigated back to the same convenience store last night, drove through crazy cars scrambling to gas pumps, navigated out of the parking lot correctly, drove me home, and, once again, parked in my assigned spot.

As previously stated, this release just seems to have a few things that need to be brought to Tesla’s attention, and also to make others who use FSD aware of some things that I’ve experienced. I look forward to the next release that will remedy these issues, just as Tesla has always done in the past.

Continue Reading

Elon Musk

Musk’s massive Terafab project will get final location soon

Published

on

Credit: SpaceX

Elon Musk’s massive Terafab project, which will be the first true conglomeration between each of his major entities, is set to get its final location soon, the CEO said on Tesla’s recent earnings call.

“The Terafab, we expect to announce a location soon, and provide more details about our plans in that regard. We’ll leave that to the product, the launch announcement rather than try to squeeze it into an earnings call,” Musk said last Wednesday.

Tesla Terafab set for launch: Inside the $20B AI chip factory that will reshape the auto industry

Terafab was announced by Musk back in March and was essentially a massive, vertically integrated semiconductor manufacturing project that would provide all the chips the three companies needed for their AI initiatives without needing third-party companies.

The plant will produce over 1 terawatt of AI compute each year, and will help back up projects like Optimus, Full Self-Driving, and other AI-based projects that Musk’s companies are working on.

In April, less than a month after the project was launched, Intel announced it would join the project, contributing manufacturing expertise and consulting to Terafab as a whole. Intel is one of three chip manufacturers that produce sub-5 nanometer chips at scale. TSMC and Samsung are the other two.

However, there was no true indication of where Terafab would end up, but most believe it will likely be somewhere in Texas. Business Insider has reported that SpaceX plans to build out Terafab in Grimes County, Texas, but this is unconfirmed.

Musk confirmed recently that it would not be on Giga Texas property, as it is simply too large.

Terafab holds much of Musk’s grand ambitions for the future within its construct. It holds so much responsibility for the future and the biggest projects that Musk’s companies can imagine.

“I think this is a very big announcement and it deserves to have its own day in the spotlight and not be squeezed into an earnings call,” he said. “I do think Terafab is going to be an amazing initiative and a necessary one, and one without which we will be constrained in our ability to scale Optimus production, because we simply won’t have enough AI chips.”

He continued by stating that Terafab is necessary for scaling Optimus, which Musk said could be the biggest product of any kind of all time. “It’s crucial to solve that, and we’ll have to solve memory, logic, and packaging in order to scale Optimus.”

Continue Reading

Elon Musk

Tesla FSD takes owner on a 20,000+ mile joy ride

Tesla owner David Moss just pushed his intervention free FSD streak past 20,000 miles total.

Published

on

By

Tesla FSD 14.3 [Credit: TESLARATI)

Tesla Model 3 owner David Moss has spent the better part of eight months turning his vehicle into a rolling stress test for Full Self-Driving, and this week he pushed his single, continuous FSD streak past 20,000 miles without a human intervening.

Moss, a Tacoma, Washington resident who sells LiDAR scanning equipment for a living, first drew wide attention in December 2025 when he logged 10,000 consecutive miles on FSD v14.2. Days later he drove from the Tesla Diner in Los Angeles to Myrtle Beach, South Carolina, covering 2,732 miles in two days and 20 hours with zero disengagements, the first verified coast to coast autonomous drive in Tesla’s history. Tesla even featured the trip as an official customer story in March. That original streak eventually reached 12,961 miles across 30 states before ending in rural Wisconsin in January, when snow and single digit temperatures forced Moss to take over.

Tesla FSD successfully completes full coast-to-coast drive with zero interventions

He started over, and this run has gone further. In late May, Moss drove 3,760 miles across Canada with two companions, from Horseshoe Bay in Vancouver to a Tesla showroom in Halifax, again without a single intervention, a trip Tesla AI software VP Ashok Elluswamy publicly congratulated him for on X. In June, he pushed the same unbroken streak south, aiming to link the Canadian border to the Mexican border, and crossed 10,000 miles on Tesla’s newly added in car streak counter along the way, the first driver to do so since Tesla began showing confetti animations for the feature.


It’s worth noting that every mile is logged through the FSD Database, a community run tracker built by Tesla influencer Omar Qazi, well known as @WholeMars on X, that pulls telemetry straight from the car and records disengagements down to a tenth of a mile. That verification is what separates Moss’s numbers from casual claims on social media.

The streak itself is a fairly recent addition to Tesla’s software. FSD v14.2 introduced a Self Driving Stats panel tracking the ratio of autonomous to manual miles, and v14.3.4 added the live streak counter in June, which resets the moment a driver brakes, wrenches the wheel or cancels navigation. Reaching 20,000 miles on that counter means a single Tesla drove itself through countless highways, city grids, construction zones and Supercharger stalls without a single reset.

Moss has said the goal was never to set a record for its own sake, but to show, mile by verified mile, what the software can already do.

Continue Reading