zlacker

>>tim_sw+(OP)
Our goal is to build a roughly human-level automated alignment researcher. We can then use vast amounts of compute to scale our efforts, and iteratively align superintelligence.

Not for nothing, but in the movie script version it’s the “human-level automated alignment researcher” that actually triggers the robot apocalypse.

>>twoodf+1H1
That’s a bit less concerning to me than this:

deliberately training misaligned models