Richard Loosemore

Can a future artificial intelligences be made safe? And assuming AI Safety is feasible at all, will it turn out to be an easy problem to solve, or an extremely hard problem? Right now, there is a feeding frenzy under way (Jaan Talinn called it an “ecosystem”), involving a number of groups and individuals who want to persuade charities to give them money …

[Note.  This is a project proposal that was written in 1989.  Published here for the first time because it has some historical relevance … which is to say, some of the ideas I am working on today were already contained in this 1989 paper.] Introduction The eventual goal of this research is to construct a …

In a recent blog post titled Maverick Nannies and Danger Theses, Kaj Sotala gave a long and thoughtful response to my 2014 AAAI paper The Maverick Nanny with a Dopamine Drip: Debunking Fallacies in the Theory of AI Motivation (a pdf of the original paper is here but there’s also a blog post version here). The focus of Kaj’s essay was actually …

How to Build an AGI — and How Not To So, you want to build an artificial general intelligence? One approach is to turn your AI investment money into a large pile of cash and then burn it. That worked for a lot of people over the last sixty years, so don’t feel bad. But on the off chance that (a) you actually want …

… or The Maverick Nanny with a Dopamine Drip Richard P. W. Loosemore Abstract My goal in this essay is to analyze some widely discussed scenarios that predict dire and almost unavoidable negative behavior from future artificial general intelligences, even if they are programmed to be friendly to humans. I conclude that these doomsday scenarios involve …

Can we build a benevolent AI, and how do we get around the problem that humans cannot define ‘benevolence’? People seem concerned at how many different definitions of “benevolence” there are in the world — the point being that humans are very far from agreeing a universal definition of benevolence, so how can we expect to program …

Reinforcement learning, the way it is now practiced in AI, is just old-fashioned Behaviorism on modern steroids, so here is my take on Behaviorism, for anyone who is into that whole not-repeating-the-mistakes-of-history thing. The Behaviorist paradigm, as it originally appeared in the field of psychology, says that an intelligent system looks at the current state of the …