As researchers use AI systems, they will identify recurring weaknesses and address them through human feedback or purpose-built training environments.

“People will in practice do some combination of those two things and just each iteration like patch whatever seems to be most broken in the last iteration. So like researchers will be using the AIs a lot and will notice that they have some consistent weaknesses and then those things will either be patched by like collecting human feedback or like creating environment.”

“the environments”