Last week, we reported regressions found in the previous FSD v14.3.6 update. These were mostly related to hesitant braking (brake-stuttering) in various scenarios and parking issues.
Tesla responded quickly to user feedback and media reports on the previous FSD v14.3.6 update and began rolling out FSD v14.3.7 this week.
It’s been a couple of days since many Tesla owners have installed the new FSD v14.3.7 (firmware version 2026.21.5) software update (release notes below).
Generally, multiple early access beta testers are posting positive feedback on FSD v14.3.7. However, one tester reported that this version is missing highway exits the same way as FSD v14.3.6 did.
In the early tests on the same routes and similar traffic conditions, Tesla owners have found the brake-stabbing or stuttering to have been fixed in this new installment of Tesla’s Full Self-Driving (Supervised).
Autonomous parking and unparking functions have also been improved in FSD v14.3.7 (videos below).
FSD v14.3.7 Rollout Status
Although it has been a few days since the FSD v14.3.7 rollout began, it’s still in limited release. Most of the original early access members and YouTube/X influencers are getting this new version of Full Self-Driving.
According to the Tesla software tracking websites TeslaFi.com and Tessie.com, FSD v14.3.7 is installed on less than 1% of the HW4 Tesla vehicle fleet.
FSD v14.3.7: Video Reviews
Several Tesla YouTubers and influencers on X are posting their short and long reviews of the new FSD v14.3.7 update. Some say it is the best version of FSD yet, while others say there are still issues to address from the previous update’s quirks.
Long Form Tests
Chuck Cook and Black Tesla from YouTube have been reviewing and testing Tesla’s Full Self-Driving AI software for years now. Both of them have posted the following long-form videos of FSD v14.3.7 on their channels.
Black Tesla posted a nearly half-hour FSD v14.3.7 test drive, and this test shows that the brake-stabbing issue has been fixed in this update.
However, in Chuck Cook’s test, FSD v14.3.7 failed in an angled-parking test. He described his experience as “two situations of horrible parking”. Parking at a Supercharger was fine, though.
Short-Form Tests
Official Release Notes: FSD v14.3.7 (2026.21.5)
Full Self-Driving (Supervised) v14.3.7 includes:
- 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.
- Rewrote the AI compiler and runtime from the ground up with MLIR2, resulting in 20% faster reaction time and improving model iteration speed.
- Mitigated unnecessary lane biasing and minor tailgating behaviors.
- Increased decisiveness of parking spot selection and maneuvering.
- Improved parking location pin prediction, now shown on a map with a (P) icon.
- Enhanced response to emergency vehicles, school buses, right-of-way violators, and other rare vehicles.
- Improved handling of small animals by focusing RL1 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.
- 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.
- Unified the model between Actually Smart Summon, FSD, and Robotaxi for more capable and reliable behavior.
- Actually Smart Summon max speed is now increased to 8mph (13km/h).
- Help Tesla improve Self-Driving by selecting an intervention reason on the main screen after taking over.
- You can now see distance traveled in FSD (Supervised) without an intervention. The Self-Driving App will also show your longest intervention-free streak.
- Parking options now display on the map when arriving at your destination.
Upcoming Improvements
- Expand reasoning to all behaviors beyond destination handling.
- Add pothole avoidance.
Acronyms used:
- RL = Reinforcement Learning
- MLIR = Multi-Level Intermediate Representation (MLIR)
- FSD = Full Self-Driving
- AI = Artificial Intelligence
Stay tuned for constant Tesla updates. Follow us on:
Google News | Flipboard | X (Twitter) | WhatsApp Channel | RSS (Feedly).
Related Tesla FSD News and Reviews
- Tesla owners can earn up to 12 months of free Full Self-Driving (FSD) via the Referral Program
- Tesla FSD v14.3.13 gets involved in a crash and shows multiple regressions (review videos)
- Tesla expands the rollout of 2026.38.5.11 update: FSD v14.3.13 (HW4) and FSD v14.3 Lite (HW3)
- Tesla (TSLA) Q3 2026 Earnings: 75% FSD attach rate, financial highlights, more
- Tesla rolls out FSD v14.3 Lite (2026.38.5.1) to legacy HW3 Model S/X vehicles with Intel GPU
- Tesla FSD v14.3.12 with Halloween Update (2026.38.5) goes wide release (demo videos, release notes)
, which were part of the FSD v14.3.6 update. Get extensive video reviews, rollout status, and release notes.){kind=link}