Papers
We list important papers on AGI as follows:
- Out-of-sample extension of graph adjacency spectral embedding: consider the problem of obtaining an out-of-sample extension for the adjacency spectral embedding, a procedure for embedding the vertices of a graph into Euclidean space.
- Measuring and avoiding side effects using relative reachability: introduces a general definition of side effects, based on relative reachability of states compared to a default state, that avoids these undesirable incentives.
- Asymptotically Unambitious Artificial General Intelligence: presents the first algorithm for asymptotically unambitious AGI, where “unambitiousness” includes not seeking arbitrary power; identifies an exception to the Instrumental Convergence Thesis.
Last modified 3yr ago