Akira Pyinya

Abstract This article is a brief summary of ACI's new definition of intelligence: Doing the same thing in new situations as the examples of the right thing to do, by making predictions based on these examples. In other words, intelligence makes decisions by stare decisis with Solomonoff induction, not by...

What is value? What are rewards? In traditional models of intelligence, we don't have to worry about these questions. Reward is simply what we need to maximize, and value (or utility) represents total expected rewards. You don't need to question these fundamental assumptions of the model. In contrast, ACI argues...

Most traditional AI models are dualistic. As Demski & Garrabrant have pointed out, these models assume that an agent is an object that persists over time, and has well-defined input/output channels, like it's playing a video game. In the real world, however, agents are embedded in the environment, and there's...

In the previous post, we have demonstrated that a self-improving AI would not be content with retaining its pre-programmed values. Once it has the ability to rewrite its own source code, a superintelligence can easily break down any defense system its inferior predecessor designed to protect its previous values and...

Abstract Seed AI's singularity scenario is based on the hypothesis that an AI agent can preserve its original utility function while self-improving. We argue that all value-preservation mechanisms will eventually fail because you can't encode values into someone smarter than you. Thus, a seed AI may lose the motivation to...

Goal and Utility are central ideas in the rational agent approach of AI, in which the meaning of intelligence is to achieve goals or, more explicitly, to maximize expected utility. What goal or utility function should an AI choose? This question is meaningless in the rational agents framework. It's like...

(Sorry this post has many errors, so I rewrite this chapter here) In the previous chapter, we have introduced how ACI circumvents the is-ought problem: an ought can’t be derived from an is, but what is the right thing to do can be derived from examples of doing the right...