Automated alignment researchers could extend to crisp projects like red teaming
Original titleThese AARs can also be applied to other alignment research projects that are “crisp”, i.e. where we can procedurally verify the quality o...
AISummary
Jan Leike says the same automated alignment research approach (AARs) could apply to other alignment projects whose work quality can be procedurally verified. He names automated red teaming, auditing games, and control methods as examples of such "crisp" projects.
Source: Jan Leike · x.comPublished · added here