The head of the AI alignment team at OpenAI tweeted this out earlier this month. He said that our models generalized to follow instructions in non English, even though we almost exclusively trained on English. Another one of those weird blessings of scale, you just scale up these models and they just seem to figure out how to do shit. And we don't really know how. But yeah, many, many mysteries still left,. Even though we're getting on for three years in the AI scaling game. Next up, we have AI Masters video games 6,000 times faster by reading the instructions.