Fabrizio Giordano

@DoublepPradhan @DevinOlsenn Ahah I thought the same! @DevinOlsenn u out 😂

@DevinOlsenn We enjoy her commentary over yours!! lol . You fired!!! JK

FSD V14.3 is officially installed on the car! but I’m almost 1,000 miles away from it 😩 But since Jae is such an amazing partner she has agreed to film a video this evening, so expect that to be up late tonight or early tomorrow. Exciting times!

@rhensing 10.5Gb, is this a larger release Or is it about the same size of recent updates?

Got to 50% and I got the prompt to install? 10.5Gb downloaded. Installing now!!

@wholemars I am curious if FSD 14.3 update is still 10gb or is it now larger

@mikepat711 @congressdj @DevinOlsenn this will make you appreciate FSD even more :D

@congressdj @DevinOlsenn I’m out of town driving a Nissan Altima til Friday smh

Hey @DevinOlsenn we did it! 14.3 dropped while we are both traveling! You’re welcome, Tesla fans. Devin and I did this for you.

@AIDRIVR Video or never happened! :D Looking forward to it man!

ITS HAPPENING!

@DevinOlsenn what’s your take on the “upcoming” section in the changelog? I appreciate that Tesla is upfront. It makes me think they may have scaled things back a bit to hit deadlines. In past releases, those didn’t show up this quickly. Curious to hear your thoughts sorry i asked the same question to @SawyerMerritt and @01Ananto and about to @DirtyTesLa

Pothole avoidance listed as an upcoming improvement for FSD 14.3

@SawyerMerritt @SawyerMerritt what’s your take on the “upcoming” section in the changelog? I appreciate that Tesla is upfront. It makes me think they may have scaled things back a bit to hit deadlines. In past releases, those didn’t show up this quickly. Curious to hear your thoughts. 🙏

@SawyerMerritt Love it! A little too many "upcomings" for my liking but wow looking forward to try this new 14.3

BREAKING: Tesla has officially released FSD V14.3 I'm downloading it in my Model Y right now. Here's everything that's new: • Improved parking location pin prediction, now shown on a map with a P icon. • Increased decisiveness of parking spot selection and maneuvering. • Rewrote the Al compiler and runtime from the ground up with MLIR, resulting in 20% faster reaction time and improving model iteration speed. • Enhanced response to emergency vehicles, school buses, right-of-way violators, and other rare vehicles. • Mitigated unnecessary lane biasing and minor tailgating behaviors. • Improved handling of small animals by focusing RL training on harder examples and adding rewards for better proactive safety. • Improved traffic light handling at complex intersections with compound lights, curved roads, and yellow light stopping - driven by training on hard RL examples sourced from the Tesla fleet. • Upgraded the Reinforcement Learning (RL) stage of training the FSD neural network, resulting in improvements in a wide variety of driving scenarios. • Upgraded the neural network vision encoder, improving understanding in rare and low-visibility scenarios, strengthening 3D geometry understanding, and expanding traffic sign understanding. • Improved handling for rare and unusual objects extending, hanging, or leaning into the vehicle path by sourcing infrequent events from the fleet. • Improved handling of temporary system degradations by maintaining control and automatically recovering without driver intervention, reducing unnecessary disengagements. Upcoming Improvements: • Expand reasoning to all behaviors beyond destination handling. • Add pothole avoidance. • Improve driver monitoring system sensitivity with better eye gaze tracking, eye wear handling, and higher accuracy in variable lighting conditions.

@01Ananto @01Ananto what’s your take on the “Improvements” section in the changelog? I appreciate that Tesla is upfront. It makes me think they may have scaled things back a bit to hit deadlines. In past releases, those “upcomings” didn’t show up this quickly. Curious to hear your thoughts

@fabrygio Downloading Now

Download FSD 14.3 on my Model Y. You can expect a video soon

@SawyerMerritt this is @ChuckCook and @DevinOlsenn curse! :D

@DevinOlsenn 11 days eh, which align very well with your working trip… eh eh. Well played 😁

Tesla take your time with FSD v14.3, if you need to wait another 11 days to tidy things up that’s totally okay.

We see our home planet as a whole, lit up in spectacular blues and browns. A green aurora even lights up the atmosphere. That's us, together, watching as our astronauts make their journey to the Moon.

@preta_6 Italy or by where all the lines converge

This is an impossible choice 😭

@xdavidhu @jwardell just wow. you are a driving car in your living room :D please keep posting, this is so fascinating. beside the sheer fun of it, what would be the practical applications here beside find bugs or security flaws (which is still super valuable)?

Managed to make it charge & shift into drive! -- Found a post from @jwardell with a 2018 raw CAN data recording and replayed it with a Raspberry Pi to the MCU:

@xdavidhu This is short of incredible, I am going to follow your journey on this. Do you think you can put in gear and "simulate" a drive?

Did you know you can boot up a Tesla's brain without the rest of the car? I was always curious about how Tesla cars work under the hood. To start security research on their products, I set up a Model 3's computer running on a desk, car-less: bugs.xdavidhu.me/tesla/2026/03/…

@DavidMoss @wholemars @fsd_database @RIDE_AI Can you share more about the ride ai conference?

I wouldn’t be here today in this position if it wasn’t for @wholemars & his @fsd_database Thank you Omar for everything! Look forward to getting together again April 15th at the @RIDE_AI conference in San Francisco for both of our live talks

@ReardenSteelX @SDembraski Yea same I love the yoke but no retrofit 😑

@SDembraski Wish I could get that yoke on my new X. They won’t retrofit anymore

Spent the day with the S. I was the passenger in the drivers seat for 182 miles. Very thankful to have it.

@JCChristopher You are incredible! @JCChristopher da best!

I went to the exact same location of the Cybertruck accident shown in the Fox News video. This is the US-69/59 Eastex Freeway northbound HOV lane at the Y-split near the Eastex Park & Ride exit (approaching from downtown Houston toward Humble). In the Fox News video, the vehicle failed to follow the right curve, going straight into the barrier. Well, I tested it twice today with Tesla FSD engaged the entire time with zero human intervention. And unless you think I am a hologram speaking to you from another dimension now, it worked out really well. Here is the video of me taking the exact same curve twice, with Tesla FSD v14.2.2.5.

@JCChristopher @rajuvamsi007 Video or It Didn't Happen 😅😂

@rajuvamsi007 I found the location. It's 10 miles from me. 😂I will go test it out

I am by no means saying Tesla should do this, as they have the data and I don’t. But I am going to say something, based on my own experience using FSD as an Uber driver in Houston, and seeing some of these videos: Tesla, get these people out of the drivers seat. Take the damn controls away from them. We have reached a point where human frailty and human fear is being swept under the carpet, and FSD is taking the blame for those same things. And X, please shadow ban anyone who DMs me or comments to me with their “right turn on red”, or “lane selection” or “weird parking lot navigation” questions. I would actually be ok if you give them the same treatment as Yemen does when someone illegally enters their country.