x

LESSWRONG

LW

SeanKessinger — LessWrong

SeanKessinger

SeanKessinger

Message

Independent researcher in conceptual AI alignment

AFFINE Superintelligence Alignment Seminar (fellow + online cohort facilitator)

IT/data/security experience

Open to research collaborations, facilitation, and funded work

DMs welcome

6

1

3y

SeanKessinger

Independent researcher in conceptual AI alignment

AFFINE Superintelligence Alignment Seminar (fellow + online cohort facilitator)

IT/data/security experience

Open to research collaborations, facilitation, and funded work

DMs welcome

Recognition: when an agent counts an entity as itself

Epistemic status: conceptual. I define a schema. I do not argue that existing systems recognize anything, only that the schema makes such claims and associated risks expressible. TL;DR Dan Hendrycks's Eigenism proposes aligning artificial intelligence by establishing sufficient shared history with a person, such that the AI protects the individual...