On February 22nd, 2023, I gave an introductory talk on the field of AI Alignment to the AI Journal Club at Northwestern University. Usually, we discuss a single paper each week, but I felt it was necessary to deviate from that pattern due to the limited awareness of the field, even among AI researchers. Dissecting a single alignment paper for an audience unfamiliar with the fundamental problem at hand would have been akin to teaching someone about assembly-level code optimizations when they were just learning to use a computer.

In Gödel, Escher, Bach, Prof. Hofstadter has quoted a passage from Dean Wooldridge’s book Mechanical Man, where he details an experiment involving the egg-laying habits of wasps of the genus Sphex. When it is time for the wasp to lay eggs, she finds and paralyzes a cricket with her venom, and then drags it into a burrow. She lays her eggs alongside the cricket, closes the burrow, and flies away, never to return. The eggs soon hatch, and the grubs consume the paralyzed cricket. Specifically, to bring the cricket into the burrow, the wasp performs the following steps in order: