Vanessa Kosoy
Titles as the sources gave them. In 2 entries, with 0 checked quotations.
In the Base
Every entry they appear in.
The Alignment Problem: Computer Science Meets Analytic Philosophy
In a forum post, Vanessa Kosoy sets out what the technical AI alignment problem is and its core difficulties, drawing on learning theory, analytic philosophy and views from the Machine Intelligence Research Institute. The excerpt argues that making AI safe is underspecified until the AI's task is chosen.
Preface to the Computational Agent Theory and ASI Alignment Sequence
According to the excerpt, Vanessa Kosoy opens a sequence on computational agent theory and aligning artificial superintelligence. The author argues ASI poses a grave existential risk, that making it safe needs theoretical and philosophical progress, and that any solution must meet unprecedented standards of reliability.