Ilio comments on Possible miracles

[Ilio]

Thanks for opening minds to the possibility that agents & their utility function may not be the most fruitful way to think about these questions. Could you provide a few pointers to these « notably not all » from point 5?

[Garrett Baker]

• Brain like AGI safety

• Shard Theory

• Iterated Amplification

• Much of interpretability work

• Possibly Pragmatic AI Safety, idk much about it.

• The selection theorems branch of research

• The particular selection theorem case of modularity

[Ilio]

Thanks! By interpretability work, you mean in the vein of Colah and the like?

[Garrett Baker]

Yes