Recently the renowned Machine Intelligence Research Institute (MIRI) published an extensive interview with IIIM Director Kristinn R. Thorisson on the subject of Constructivist AI — a methodology and approach to building artificial general intelligent systems (AGI) that Thórisson and his colleagues have been developing for the past decade. The full article can be found on Miri’s website.

Formerly known as the Singularity Institute, MIRI is perhaps the most well known authority in the field of AGI, acting as both conscience for AGI research as well as a general exponent of research in the field. Their express goal is to ensure that creation of smarter-than-human intelligence has a positive impact on the world.

The interview touches on a number of subjects relating to AGI and serves as an excellent overview of Thorisson’s Constructivist Design Methodology.

“I had been working on integrated constructionist systems for close to two decades, where the main focus was on how to integrate many things into a coherent system. When my collaborators and I started to seriously think about how to achieve artificial general intelligence we tried to explain, among other things, how transversal functions – functions of mind that seem to touch pretty much everything in a mind, such as attention, reasoning, and learning – could efficiently and sensibly be implemented in a single AI system.” – K. R. Thorisson

The interview goes on to compare constructivist AI with other related approaches to building artificial general intelligence and how they vary. For those lesser inclined towards the details of academic AI research the interviewer also touches on the broader aspects of AGI; specifically whether safety precautions are needed and how dangerous truly intelligent systems could be if handled incorrectly.