What is it about?
The field of Artificial General Intelligence needs a simple and understandable measure of progress to aid in passing the difficult Turing Test. The proposed Ladder Metric introduces a sequence of levels that intelligent agents must climb in order to reach the final, Turing indistinguishable, level. Just like the Turing test, the levels can only be defined in terms of general properties and behavior rather than specific operational requirements. To track the progress and make comparisons one must climb and determine the achieved rung of the proposed ladder.
Featured Image
Why is it important?
The ladder helps both to build strong AI and to understand the pitfalls many existing approaches fail to identify. It is the first metric to actually show the true state of any human-like AI.
Perspectives
The presented ladder, I believe, more clearly shows obstacles on the path towards true human-comparable intelligence. Because of our not understanding of the intelligence in general, it is still not fully elaborated yet has the potential to reach the AGI.
Matej Šprogar
University of Maribor
Read the Original
This page is a summary of: A ladder to human-comparable intelligence: an empirical metric, Journal of Experimental & Theoretical Artificial Intelligence, August 2018, Taylor & Francis,
DOI: 10.1080/0952813x.2018.1509897.
You can read the full text:
Contributors
The following have contributed to this page
