깜짝아 가자!!!!!!!!
FSD v15 now starting to roll out – upgrading every part of the end-to-end driving network
Safety
25x better handling of safety critical cases
Tesla Reality View
Adds a live visualization of the drive that lets you see & control what FSD is planning to do
Navigation for start & end of the trip now learns end-to-end from fleet route preferences. Later v15 releases will expand this to the entire route.
You also should notice better detection of signs, animals, debris, potholes and standing water, plus more natural speed handling in school zones and inclement weather.
Lastly, FSD can now slow for speed cameras & Bike Rack Mode lets you enable FSD w/ bike racks or similar hitch accessories
네온이 좋긴 좋나보네요 😶
i'm admittedly pretty harsh on the google guys, mostly cuz i know the co super well.
but holy hell, i'm having an incredible time with neon so far.
product issues aside, this is a very different experience, almost like a strange new feeling. the way it talks, the way it responds, everything feels pretty damn fresh if that makes any sense. it's very creative. & unusually great at proposing ideas. i can't even say it's about intelligence or better answers in general. i am normally okay with words, but this is very difficult for me to articulate well.
anyway, it's fairly clear that google absolutely cooked here.
i have never doubted google's technical capabilities. those were & are totally obvious. i mean it is literally the birth place of ai. it was always a question of whether google could turn an extraordinary technology into newer experiences that ppl love using, which sort of requires shedding every success of the past.
these newer generation of models, particularly neon clearly gives them extraordinary new legs to stand on. it doesn't feel like "gemini" at all.
congratulations to everyone at google, i will continue to play around with more. there are obviously some product frustrations & confusing elements but i'm setting those aside for now.
10
Replying to @BLKMDL3 @wholemars
In case anyone is curious:
We’ve had a ~pixel-perfect world model since last year, which is critical for synthetic data generation.
The (much) smaller version of that in the car is a conditional mean-flow model, based on the recent sequence of Tesla Universal Vision Encoder features, which are the same ones that are plugged into the 3B encoder model that produces the driving actions.
We fork off from these UVE features, then run a separate ~1B diffusion model. This takes in the previous reality-view generation with added noise and then denoises it to the current visualization.
It then produces a small video chunk (8 images at 36 fps, at the resolution of the UI screen). This work is done by 1/2 of a TRIP engine every UVE frame at 18 hz and is spread over 4 cycles.
Currently, the latency is a bit high due to compute constraints, but we have ways to interleave newer UVE features along the diffusion transformer layers to cut roughly 35% of the latency.
Tony retweeted
Full release notes below
– – –
v15 upgrades every part of the end-to-end driving network. Includes:
Upgraded vision encoder shared between FSD, Robotaxi, and Optimus, which is trained on millions of internet videos for improved generalization and data efficiency, improving the critical intervention rate by 25x.
Introduced Tesla Reality View, replacing all of the explicit model signals into a single end-to-end visualization using less total compute.
Improved navigation by using an end-to-end learned model based on route preference data from the fleet.
Improved parking location selection by using personalized parking history, and the map will now display multiple parking options at your destination.
Improved driver monitoring by increasing vision-based attention monitoring availability with hats and sunglasses and decreasing strictness in higher speed driver profiles.
Improved detection of road signs, small animals, road debris, and chains.
Improved detection of potholes, road details, and avoidance of deep standing water.
Improved speed handling for each driver profile, school zones and speed limits, and inclement weather.
Improved Autoshift functionality by unifying with FSD-based gear predictions.
FSD v15 now starting to roll out – upgrading every part of the end-to-end driving network
Safety
25x better handling of safety critical cases
Tesla Reality View
Adds a live visualization of the drive that lets you see & control what FSD is planning to do
Navigation for start & end of the trip now learns end-to-end from fleet route preferences. Later v15 releases will expand this to the entire route.
You also should notice better detection of signs, animals, debris, potholes and standing water, plus more natural speed handling in school zones and inclement weather.
Lastly, FSD can now slow for speed cameras & Bike Rack Mode lets you enable FSD w/ bike racks or similar hitch accessories
Tesla Hiring Equipment Maintenance Technician for Optimus Precision Machining!
Tesla is recruiting a full-time Equipment Maintenance Technician in Lathrop, California, to support Optimus-related precision machining operations.
Key responsibilities include maintaining and repairing industrial production equipment, robotic automation systems, troubleshooting machinery, and improving production line reliability.
The role involves working with PLCs, hydraulic and pneumatic systems, and industrial robotics.
This hiring reflects Tesla's efforts to strengthen the manufacturing infrastructure and technical workforce supporting Optimus production.
$TSLA
Tony retweeted
Most insane driving moment yet. I was supposed to turn right, but right before this clip took over and turned away from nav to show a pothole heavy road. You can hear me wondering why the car is going so slowly/thinking it’s messing up. But no. It’s actively ignoring nav, which rerouted and had us going straight, and instead finding a way to turn around to get back onto the shorter route.
Insane shit. Have never seen behavior like that before
봐야 보이고 믿는다
사이버캡
로드스터
V15
옵티머스 (sublime)
Replying to @niccruzpatane
We haven’t shown Optimus V3 yet. It is sublime. The second two images are V2 and V2.5.
22















