Tesla able to produce real-world video similar to OpenAI’s for over a year: Musk
Musk said, "Tesla has been able to do real-world video generation with accurate physics for about a year"
New Delhi: Tesla CEO Elon Musk has shared intriguing insights into the potential synergies between OpenAI’s Sora and his own autonomous driving ambitions after the ChatGPT maker unveiled its text-to-video model.
Responding to a video captioned ‘What does @OpenAI’s Sora have to do with @Tesla’s FSD (Full Self-Driving) v12?’ on X, Musk said, “Tesla has been able to do real-world video generation with accurate physics for about a year”.
However, the tech billionaire mentioned that the videos were not much interesting since the real-world training data comes only from the electric automaker’s camera-equipped fleet.
“It wasn’t super interesting, because all the training data came from the cars, so it just looks like video from a Tesla, albeit with a dynamically generated (not remembered) world,” Musk added.
In the video, the host compares the research paper from both companies approaching video generation for two completely different reasons and from two completely different paths and converging on the same solution.
Moreover, the Tesla CEO mentioned that the company have been short on training compute for FSD, “so haven’t trained with other video, but certainly could. Will do it later this year when we have some spare capacity”.
Meanwhile, Tesla has rolled out FSD version 12.12 to customers. The new update promises notable progress for the company’s self-driving software.
