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)
On self play:
“Self-play has a property that it can surprise us in truly novel ways.” (e.g., creative solutions to problems that weren’t anticipated — and are actually useful!)
People can also be worst than expected. Everything is a matter of perspective. Is better to build yourself in a way that the reaction of other people will not influence your balance 😊