Epstein Secrets

Leg06b. Shane Legg. Unprovability of friendly ai. Vetta Project, 2006. ht tp: / /www vette.org/2006/ 09/unprovability -of -friendly -ai/. LG90. Douglas Lenat and R. V. Cuba. Building Large Knowledge-Based Systems: Representation and Inference in the Cyc Project. Addison-Wesley, 1990. LH07a. Shane Legg a

oduced in IWin71. Certainly a pure "Blocks World with Glue" would have greater simplicity than BlocksNBeadsWorld, and greater richness than standard Blocks World; but this simplicity comes with too many limitations, as shown by consideration of the various naive physics requirements inventoried above. One si

nk. pdf. Leg06b. Shane Legg. Unprovability of friendly ai. Vetta Project, 2006. http: //www.vetta.org/2006/ 09/unprovability-of-friendly-ai/. LG90. Douglas Lenat and R. V. Guha. Building Large Knowledge-Based Systems: Representation and Inference in the Cyc Project. Addison-Wesley, 1990. LH07a. Shane Legg and

oduced in [Win72]. Certainly a pure “Blocks World with Glue” would have greater simplicity than BlocksNBeadsWorld, and greater richness than standard Blocks World; but this simplicity comes with too many limitations, as shown by consideration of the various naive physics requirements inventoried above. One simp

following participants: Larry Birnbaum (Northwestern University), Ken Forbus (Northwestern University), Ben Kuipen (University of Texas at Austin), Douglas Lenat (Cycorp), Henry Lieberman (Massachusetts Institute of Technology), Henry Minsky (Laszlo Systems), Marvin Minsky (Massachusetts Institute of Technol

g reasoning in each of these realms. He suggested that we develop our architectures within a physically realistic model world resembling the classic Blocks World, but where the world was populated by several simulated beings, and thus emphasizing social problems in addition to physical ones. These beings wou