Conversation

On transformers: Transformers are successful because they are a simultaneous combination of multiple ideas: attention, ability to run quickly on a GPU, non-recurrence (and therefore less deep so easier to optimize)
1
15
Replying to
On the goodness of people: “I don’t know if most people are good, but I think that when it really counts people can be better than you think.” ♥️
2
7
75