sudhanshu_kasewa

Wiki Contributions

Comments

Sorted by

No, this is not something I can undertake -- however, the effort itself need not be very complicated. You've already got a list of Misalignment types in the form: create a google doc with definitions/descriptions of each of these, and put a link to that doc in this question.

It might be worth (someone) writing out what is meant by each kind of misalignment category, as used in the db. Objective misalignment, specific gaming, value misalignment all seem overlapping, and I'm not at all sure what physical misalignment is supposed to be pointing to.

Answer by sudhanshu_kasewa10

Anthropic

Answer by sudhanshu_kasewa10

The EU parliament

Answer by sudhanshu_kasewa10

The UK government

Answer by sudhanshu_kasewa10

Vladimir Putin

Answer by sudhanshu_kasewa20

The Chinese Communist Party

Answer by sudhanshu_kasewa10

The American Public

Answer by sudhanshu_kasewa20

Joe Biden

Load More