I felt like frontier labs need to teach everybody how to do alignment research without math. Speed up research because those who in power never slow down their “strategic advantages”.
That’s a more realistic ask than hoping everyone slows down: If alignment methods can be made accessible to engineers without deep math, more people can stress test, critique and improve them. Knowledge spreads far more easily than voluntary restraint, especially when geopolitical incentives point the other way.
I felt like frontier labs need to teach everybody how to do alignment research without math. Speed up research because those who in power never slow down their “strategic advantages”.
That’s a more realistic ask than hoping everyone slows down: If alignment methods can be made accessible to engineers without deep math, more people can stress test, critique and improve them. Knowledge spreads far more easily than voluntary restraint, especially when geopolitical incentives point the other way.