20-minute explainer breaks down how Tesla trains FSD: 8 cameras, 36fps, 2B signals to 2 outputs
PTrubey · x · 2026-10-10
A 20-minute explainer video breaks down how Tesla built FSD: eight cameras feed 36 frames per second—roughly 2 billion pieces of information—into a network that outputs just two numbers: steer and accelerate.
- The video distills Tesla's approach into 14 ingredients and one flywheel, covering data collection, shadow mode, and fleet-learning loops
- The author frames FSD as one of the most performant robotic superintelligence models, a useful primer on end-to-end vision-based driving
More from Embodied
- SJTU's UVTA teaches robot dexterous manipulation from 1,000 human tactile demos per task — siyuanhuang95 · 2026-10-10
- SpaceX building industrial base to make up to 1,000 Starships a year, with Florida GigaBay 11x bigger than current Megabay — XFreeze · 2026-10-10
- Real Steel IRL: Humanoid Robots Noisy Boy and Raider-72 Box Each Other — zealcaiden · 2026-10-10
- Dyna launches Taku semi-humanoid robot to remove the human babysitting bottleneck — JasonMa2020 · 2026-10-10
- First-ever humanoid deathmatch was absolutely wild — cixliv · 2026-10-10
- QWM method: morphology encoder, adaptive reward normalizer, and latent morphology conditioning — breadli428 · 2026-10-10