Compression, The Fermi Paradox and Artificial Super-Intelligence

TL;DR

Explores the problem of communicating with non-human or artificial general intelligences and the risk that intent and meaning are not aligned due to divergent priors. The approach uses a symbolic abstraction view where meaning depends on shared task framing and the ability to infer subgoals from observed behavior, invoking the mirror symbol hypothesis. It highlights compression limits via Kolmogorov Complexity $K(x)$ and the phenomenon that more compressed representations can look like noise to humans without the proper decoder. It argues that a super-intelligent AGI would construct highly compressed, intensional solutions, making its rationale potentially uninterpretable to humans. As a practical implication, safe control may require constraining the AI's cognitive strategies, which could entail a trade-off with generalization or flexibility.

Abstract

The following briefly discusses possible difficulties in communication with and control of an AGI (artificial general intelligence), building upon an explanation of The Fermi Paradox and preceding work on symbol emergence and artificial general intelligence. The latter suggests that to infer what someone means, an agent constructs a rationale for the observed behaviour of others. Communication then requires two agents labour under similar compulsions and have similar experiences (construct similar solutions to similar tasks). Any non-human intelligence may construct solutions such that any rationale for their behaviour (and thus the meaning of their signals) is outside the scope of what a human is inclined to notice or comprehend. Further, the more compressed a signal, the closer it will appear to random noise. Another intelligence may possess the ability to compress information to the extent that, to us, their signals would appear indistinguishable from noise (an explanation for The Fermi Paradox). To facilitate predictive accuracy an AGI would tend to more compressed representations of the world, making any rationale for their behaviour more difficult to comprehend for the same reason. Communication with and control of an AGI may subsequently necessitate not only human-like compulsions and experiences, but imposed cognitive impairment.