One of our goals is to have Optimus learn straight from internet videos of humans doing tasks. Those are often 3rd person views captured by random cameras etc. We recently had a significant breakthrough along that journey, and can now transfer a big chunk of the learning directly from human videos to the bots (1st person views for now). This allows us to bootstrap new tasks much faster compared to teleoperated bot data alone (heavier operationally). Many new skills are emerging through this process, are called for via natural language (voice/text), and are run by a single neural network on the bot (multi-tasking). Next: expand to 3rd person video transfer (aka random internet), and push reliability via self-play (RL) in the real-, and/or synthetic- (sim / world models) world. If you’re great at AI and want to be part of its biggest real-world applications ever, you really need to join Tesla right now.
@vueling is this a pre take off meal?
Great to know with your price increases you are completing all hygiene checks and maintaining exceptionally high standards!
#Aircraft#travel#oneofyourfiveaday
🗣️ “He never went a day without seeing me, he never went a day without speaking to me, asking me where my mental side was. It means a lot when you’re out for so long. The gaffer made sure he saw me everyday.”
Joe Willock on Eddie Howe 👏 #NUFC