Difference between revisions of "List of success criteria for HRAD work"
Line 1: | Line 1: | ||
− | This page is a list of success criteria that have been proposed for [[HRAD]] work. | + | This page is a list of success criteria that have been proposed for [[HRAD]] work. Most of these are correlated, so this isn't anything like a list of independent ways HRAD could succeed. The idea is to list out more concrete ways in which HRAD work will be useful. |
* resembles the work of Turing, Shannon, Bayes, etc | * resembles the work of Turing, Shannon, Bayes, etc |
Revision as of 02:14, 2 June 2020
This page is a list of success criteria that have been proposed for HRAD work. Most of these are correlated, so this isn't anything like a list of independent ways HRAD could succeed. The idea is to list out more concrete ways in which HRAD work will be useful.
- resembles the work of Turing, Shannon, Bayes, etc
- helps AGI programmers avoid mistakes analogous to the use of null-terminated strings in C
- early advanced AI systems will be understandable in terms of HRAD's formalisms [1] (need to clarify what it means to be understandable in terms of a formalism)
- helps AGI programmers fix problems in early advanced AI systems
- helps AGI programmers predict problems in early advanced AI systems
- helps AGI programmers postdict/explain problems in early advanced AI systems
- ideas from HRAD will be a "useful source of inspiration" for ML/AGI work [2]
- when applying HRAD to actual systems, there will be "theoretically satisfying approximation methods" that make this application possible [3]
- when applying HRAD to actual systems, the approximation methods used will preserve the important desirable properties of HRAD work [4]