This is the last in a series of three posts on the interlinkages between Memetics and AI Alignment. It was written as an output from the 2022 AI Safety Camp, for the ‘Impact of Memetics on Alignment’ team, coached by Daniel Kokotajlo and comprising Harriet Farlow, Nate Rush and Claudio Ceruti. Please read on to post 1 and post 2. We are not AI Safety experts so any and all feedback is greatly appreciated :)

TL;DR: Linking the concept of imitation between the domains of memetic and AI safety leads to considering how misalignment could spread memetically; this helps to identify misaligned agents able to generate a contagious spread of memes of misalignment. In particular, power-seeking agents could diffuse power-seeking tendencies to other agents under mild conditions. This work adds seminal tools to researching misalignment in multi-agent settings.

What does it mean to imitate

In memetic theory, imitation is a fundamental part of the evolutionary process of memes since it’s the primary way that provides the means for spreading, reproducing, selecting, and mutating memes. Even if selection pressure on memes is exerted internally, e.g., a single agent recalls only certain memes it was exposed to because the agent finds them easier to remember, the reproduction of memes can exist only in the presence of imitation.

In more detail, Susan Blackmore defines imitation as when an agent copies other agents' observed behaviour to achieve one of its goals (or sub-goals). Even if this concept clearly distinguishes imitation from other forms of collective learning (such as reaction to enhanced stimuli resulting from the actions of other agents), it lacks a detailed explanation of the copying function.

We can fill this gap by referring to the concept of observational learning made by Albert Bandura. Observational learning consists of observing and modelling another agent’s behaviour, without the need to clone the observed behaviour perfectly, but treating it as a learning source rather than precisely imitating it.

Combining observational learning and Blackmore’s definition produces a notion of copying another agent without explicitly and fully modelling its behaviour, but only focusing on replicating certain aspects or part of it.

This synthesis sounds intuitive since when we imitate some behaviour, we generally grasp ...

Posts

Wikitag Contributions

Comments