Why is verified superintelligence the next logical step?

What problems will it solve and how?

🧵 1/7 The history of AI from 2012 to present shows each paradigm solving previous limitations while revealing new ones. The next state-of-the-art will be Supervised RL for reasoning. It is fundamentally bottlenecked by the need for verifiable environments.

2/7

Here is a thread in paper references demonstrating that current deep learning, especially transformers are amazingly powerful for symbol manipulation already:

@GuillaumeLample, @f_charton
arxiv.org/abs/1912.01412
Solving hard integrals using deep transformers

🧵1/n

https://twitter.com/Plinz/status/1502337713315274760

A paper of my team at google, improving reasoning in large theories using contrastive learning for premise selection:

arxiv.org/abs/1606.04442