

News
Tesla FSD Beta 10.69.2.2 extending to 160k owners in US and Canada: Elon Musk
It appears that after several iterations and adjustments, FSD Beta 10.69 is ready to roll out to the greater FSD Beta program. Elon Musk mentioned the update on Twitter, with the CEO stating that v10.69.2.2. should extend to 160,000 owners in the United States and Canada.
Similar to his other announcements about the FSD Beta program, Musk’s comments were posted on Twitter. “FSD Beta 10.69.2.1 looks good, extending to 160k owners in US & Canada,” Musk wrote before correcting himself and clarifying that he was talking about FSD Beta 10.69.2.2, not v10.69.2.1.
While Elon Musk has a known tendency to be extremely optimistic about FSD Beta-related statements, his comments about v10.69.2.2 do reflect observations from some of the program’s longtime members. Veteran FSD Beta tester @WholeMarsBlog, who does not shy away from criticizing the system if it does not work well, noted that his takeovers with v10.69.2.2 have been marginal. Fellow FSD Beta tester @GailAlfarATX reported similar observations.
Tesla definitely seems to be pushing to release FSD to its fleet. Recent comments from Tesla’s Senior Director of Investor Relations Martin Viecha during an invite-only Goldman Sachs tech conference have hinted that the electric vehicle maker is on track to release “supervised” FSD around the end of the year. That’s around the same time as Elon Musk’s estimate for FSD’s wide release.
It should be noted, of course, that even if Tesla manages to release “supervised” FSD to consumers by the end of the year, the version of the advanced driver-assist system would still require drivers to pay attention to the road and follow proper driving practices. With a feature-complete “supervised” FSD, however, Teslas would be able to navigate on their own regardless of whether they are in the highway or in inner-city streets. And that, ultimately, is a feature that will be extremely hard to beat.
Following are the release notes of FSD Beta v10.69.2.2, as retrieved by NotaTeslaApp:
– Added a new “deep lane guidance” module to the Vector Lanes neural network which fuses features extracted from the video streams with coarse map data, i.e. lane counts and lane connectivities. This architecture achieves a 44% lower error rate on lane topology compared to the previous model, enabling smoother control before lanes and their connectivities becomes visually apparent. This provides a way to make every Autopilot drive as good as someone driving their own commute, yet in a sufficiently general way that adapts for road changes.
– Improved overall driving smoothness, without sacrificing latency, through better modeling of system and actuation latency in trajectory planning. Trajectory planner now independently accounts for latency from steering commands to actual steering actuation, as well as acceleration and brake commands to actuation. This results in a trajectory that is a more accurate model of how the vehicle would drive. This allows better downstream controller tracking and smoothness while also allowing a more accurate response during harsh maneuvers.
– Improved unprotected left turns with more appropriate speed profile when approaching and exiting median crossover regions, in the presence of high speed cross traffic (“Chuck Cook style” unprotected left turns). This was done by allowing optimisable initial jerk, to mimic the harsh pedal press by a human, when required to go in front of high speed objects. Also improved lateral profile approaching such safety regions to allow for better pose that aligns well for exiting the region. Finally, improved interaction with objects that are entering or waiting inside the median crossover region with better modeling of their future intent.
– Added control for arbitrary low-speed moving volumes from Occupancy Network. This also enables finer control for more precise object shapes that cannot be easily represented by a cuboid primitive. This required predicting velocity at every 3D voxel. We may now control for slow-moving UFOs.
– Upgraded Occupancy Network to use video instead of images from single time step. This temporal context allows the network to be robust to temporary occlusions and enables prediction of occupancy flow. Also, improved ground truth with semantics-driven outlier rejection, hard example mining, and increasing the dataset size by 2.4x.
– Upgraded to a new two-stage architecture to produce object kinematics (e.g. velocity, acceleration, yaw rate) where network compute is allocated O(objects) instead of O(space). This improved velocity estimates for far away crossing vehicles by 20%, while using one tenth of the compute.
– Increased smoothness for protected right turns by improving the association of traffic lights with slip lanes vs yield signs with slip lanes. This reduces false slowdowns when there are no relevant objects present and also improves yielding position when they are present.
– Reduced false slowdowns near crosswalks. This was done with improved understanding of pedestrian and bicyclist intent based on their motion.
– Improved geometry error of ego-relevant lanes by 34% and crossing lanes by 21% with a full Vector Lanes neural network update. Information bottlenecks in the network architecture were eliminated by increasing the size of the per-camera feature extractors, video modules, internals of the autoregressive decoder, and by adding a hard attention mechanism which greatly improved the fine position of lanes.
– Made speed profile more comfortable when creeping for visibility, to allow for smoother stops when protecting for potentially occluded objects.
– Improved recall of animals by 34% by doubling the size of the auto-labeled training set.
– Enabled creeping for visibility at any intersection where objects might cross ego’s path, regardless of presence of traffic controls.
– Improved accuracy of stopping position in critical scenarios with crossing objects, by allowing dynamic resolution in trajectory optimization to focus more on areas where finer control is essential.
– Increased recall of forking lanes by 36% by having topological tokens participate in the attention operations of the autoregressive decoder and by increasing the loss applied to fork tokens during training.
– Improved velocity error for pedestrians and bicyclists by 17%, especially when ego is making a turn, by improving the onboard trajectory estimation used as input to the neural network.
– Improved recall of object detection, eliminating 26% of missing detections for far away crossing vehicles by tuning the loss function used during training and improving label quality.
– Improved object future path prediction in scenarios with high yaw rate by incorporating yaw rate and lateral motion into the likelihood estimation. This helps with objects turning into or away from ego’s lane, especially in intersections or cut-in scenarios.
– Improved speed when entering highway by better handling of upcoming map speed changes, which increases the confidence of merging onto the highway.
– Reduced latency when starting from a stop by accounting for lead vehicle jerk.
– Enabled faster identification of red light runners by evaluating their current kinematic state against their expected braking profile.
Press the “Video Record” button on the top bar UI to share your feedback. When pressed, your vehicle’s external cameras will share a short VIN-associated Autopilot Snapshot with the Tesla engineering team to help make improvements to FSD. You will not be able to view the clip.
Don’t hesitate to contact us with news tips. Just send a message to simon@teslarati.com to give us a heads up.
News
SpaceX calls off Starship 10 flight attempt once again
SpaceX is calling off a potential launch of Starship this evening, marking the second consecutive night the tenth test flight of the massive rocket will be delayed.

SpaceX is calling off a potential launch of Starship this evening, marking the second consecutive night the tenth test flight of the massive rocket will be delayed.
Originally planning to launch on Sunday at 6:30 p.m. local time in Starbase, Texas, SpaceX was forced to delay the tenth launch of Starship due to a hardware issue.
“Ground side liquid oxygen leak needs to be fixed. Aiming for another launch attempt tomorrow,” CEO Elon Musk posted on the social media platform X.
Starship Flight 10 rescheduled as SpaceX targets Monday launch
The launch was then pushed to Monday night, and the launch window was set to start at the same time as Sunday. However, SpaceX would push it back to 6:44 p.m. due to some weather issues.
Eventually, Starship seemed like it was trending toward a launch, but weather continued to persist in the area, with thunder, rain, and lightning all threatening in the area.
At around 7:03 p.m., SpaceX decided to stand down once again, confirming weather was the culprit of yet another delay:
Launch called off for tonight due to anvil clouds over launch site (lightning risk)
— Elon Musk (@elonmusk) August 26, 2025
SpaceX will likely try again on Tuesday night, but the company has not yet confirmed if it will open another launch window.
News
WATCH: SpaceX Starship Flight 10 launch

SpaceX is set to launch its tenth test flight of the Starship program, with a launch window that will open at 6:44 p.m. local time, or 7:44 p.m. on the East Coast.
Starship’s tenth test flight was originally scheduled for launch yesterday with a one-hour window that opened at 7:30 p.m. ET, but it was called off 17 minutes before that window even had a chance to open.
Starship Flight 10 rescheduled as SpaceX targets Monday launch
SpaceX moved the flight to tonight. It was also originally scheduled to have a launch window at the same time as Sunday, but it was pushed back 14 minutes to around 6:30 p.m. ET. There are storms in the area, as well as clouds over Starbase, so there is the off chance for another launch delay.
There are several big objectives for this launch, including the expansion of the operating envelope for the Super Heavy booster. SpaceX says there are “multiple landing burn tests planned.”
The booster will also be performing a few in-flight experiments to help with data collection. Specifically, real-world performance data on future flight profiles and off-nominal scenarios will be on the list of things SpaceX will be looking for.
Starship itself will have a few in-flight objectives that include the deployment of eight Starlink simulators that are similar in size to the next-gen satellites for the internet service. SpaceX was set to test this with Starship’s seventh test flight, which occurred in January 2025. However, the task was abandoned as the vehicle was destroyed before deployment could occur.
Liftoff conditions are currently looking favorable, and SpaceX will be eager to improve upon its Starship launch program as CEO Elon Musk has big plans for it in the coming years.
You can watch the launch below via SpaceX:
Watch Starship’s tenth flight test → https://t.co/UIwbeGoo2B https://t.co/MQg9ZAjCip
— SpaceX (@SpaceX) August 25, 2025
Elon Musk
Tesla looks to expand Robotaxi geofence once again with testing in new area
It looks as if Tesla is preparing for its next expansion of the geofence, potentially moving toward a much larger service area that could eclipse 150 square miles.

Tesla looks to be preparing for the potential expansion of the Robotaxi geofence once again, as the company was spotted testing the suite in an area well outside of the Austin service area.
After it first launched the Robotaxi platform on June 22, Tesla has managed to expand its geofence twice, essentially doubling the travel area both times.
The most recent expansion took the size of the geofence from 42 square miles to about 80 square miles, bringing new neighborhoods and regions of the city into the realm of where the driverless vehicles could take passengers.
However, it looks as if Tesla is preparing for its next expansion of the geofence, potentially moving toward a much larger service area that could eclipse 150 square miles.
Over the weekend, one fan noticed a Robotaxi validation vehicle testing in Bee Cave, Texas, which is roughly 25 minutes from the edge of the current geofence:
Tesla spotted doing Robotaxi validation testing in Bee Cave, Texas, about 15 miles west of Austin (20-25 minute drive from current edge of geofence). pic.twitter.com/JCOcoys8SJ
— Sawyer Merritt (@SawyerMerritt) August 23, 2025
Tesla has been testing vehicles in the western suburbs of Austin for some time, and it seems the company is laying some groundwork to push its geofence expansion into Plaid Mode as competition with Waymo continues to be at the forefront of the conversation.
Waymo has been expanding with Tesla for some time, as the pace of expansion for the two companies has been relatively accelerated for the past couple of months.
Tesla’s expansions of the geofence sent a clear message to competitors and doubters, but it is still aiming to keep things safe and not push the envelope too quickly.
The geofence expansion is impressive, but Tesla is also focusing on expanding its vehicle fleet in both Austin and the Bay Area, where it launched a ride-hailing service in July.
Tesla Bay Area autonomous fleet to grow to over 100 units: Elon Musk
Still, safety is the priority at the current time.
“We are being very cautious. We do not want to take any chances, so we are going to go cautiously. But the service areas and the number of vehicles in operation will increase at a hyper-exponential rate,” CEO Elon Musk said during the Q2 Earnings Call.
-
Elon Musk4 days ago
Elon Musk takes aim at Bill Gates’ Microsoft with new AI venture “Macrohard”
-
News2 weeks ago
Tesla Model Y L spotted in Europe ahead of expected September China launch
-
Elon Musk23 hours ago
Elon Musk argues lidar and radar make self driving cars more dangerous
-
Elon Musk2 weeks ago
Tesla CEO Elon Musk confirms Robotaxi is opening to the public: here’s when
-
News2 weeks ago
Tesla flexes its most impressive and longest Full Self-Driving demo yet
-
Elon Musk6 days ago
Tesla’s Elon Musk shares optimistic teaser about FSD V14: “Feels sentient”
-
News6 days ago
Tesla offers new deal on used inventory that you won’t want to pass up
-
Elon Musk2 weeks ago
Tesla warns consumers of huge, time-sensitive change coming soon