John Schulman
@johnschulman2
@thinkymachines. Interested in reinforcement learning, alignment, birds, jazz music
加入 May 2021
2.1K 正在关注 79.5K 粉丝
Seeing the demos come together over the last week has been awesome -- so many things that previously required a special-purpose model (e.g. real-time translation, event detection in video) turn out to be zero-shot instruction following once you have a general-purpose model with the right type signature -- continuous/simultaneous audio+video+text->audio+text
显示更多
