On November 21, Tesla announced on X that FSD v15 is starting to roll out, upgrading every part of its end-to-end driving network, with 25x better handling of safety-critical cases and a new tap-to-go Tesla Reality View. Elon Musk later said the new in-car view is real-time AI video generation, with no game engine, running on half of one AI4 accelerator, and Tesla AI lead Ashok Elluswamy said it uses less compute than the old visualization.
Key Takeaways
- ✓Release: Tesla's official X account says FSD v15 is starting to roll out, upgrading every part of the end-to-end driving network; rollout pace and eligible vehicles were not stated
- ✓Safety: Tesla claims 25x better handling of safety-critical cases, a company-stated figure with no test method or third-party data attached
- ✓Reality View: a live view that shows what FSD plans to do and lets drivers control it; Elon Musk says you can tap any point to make the car go there
- ✓Real-time generation: Musk says the new view is real-time AI video generation with no game engine, using half of one AI4 accelerator; Ashok Elluswamy says it uses less compute than the old visualization; neither shared model details
- ✓Also: trip start and end now learn end-to-end from fleet route preferences; better detection of signs, animals, potholes and standing water, slowing for speed cameras, and a new Bike Rack Mode
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
In-Depth Technical Analysis
Background
End-to-end neural networks are now the core of Tesla FSD: one model from video to controls instead of hand-written rules. The hard parts are rare safety-critical cases and letting drivers understand and trust the system's decisions. On November 21, Tesla announced on X that FSD v15 is starting to roll out.
What changed
Tesla says v15 upgrades every part of the end-to-end driving network and adds Tesla Reality View, a live view of what FSD plans to do; Elon Musk added on X that you can tap any point in the view to make the car go there. Later, Tesla AI lead Ashok Elluswamy compared the old and new in-car views on X, saying the new one uses less compute than the old one did. Musk, quoting him, called it real-time AI video generation with no game engine, using just half of one AI4 accelerator (post). Navigation for the start and end of a trip now learns end-to-end from fleet route preferences.
Numbers that matter
The only figures are 25x better handling of safety-critical cases and the "half an AI4" compute claim. Both are company-stated, with no test method, model size or third-party data published.
What it means
v15 also improves detection of signs, animals, potholes and standing water and adds Bike Rack Mode; rollout pace was not stated. For developers, generating a live view on a small on-device compute budget to show a model's plan is a direction worth watching.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.