Commonsense for a change

Credit: King's College London

Quantum mechanics proves there is no certitude so shit happens, always. The way to deal with this is to employ commonsense, flexibility and pragmatism to, in this instance, work with possible emerging AGIs (Artificial General Intelligence(s)) to insure proper alignment with us rubes becomes the norm and not the exception.

Public concern about AI safety has grown significantly in recent years. As AI systems become more powerful, a key question is how we make sure they do what we actually want. Now, researchers suggest that rather than trying to eliminate misalignment between AI and humans, we should embrace and manage it through a diverse ecosystem of AI systems that can balance and correct one another.

"While we have shown that sufficiently strong AI cannot be fully controlled or predicted, we also demonstrate that agents can be influenced by other agents without central control, and that greater diversity and openness influence their behavior. As these systems get more powerful, ensuring they remain beneficial to and aligned with humanity becomes more important," said Dr. Hector Zenil, senior author and Senior Lecturer/Associate Professor at King's Institute for AI and the School of Biomedical Engineering & Imaging Sciences/

Published in PNAS Nexus, the paper uses mathematical principles to demonstrate that an AI system powerful enough to exhibit artificial general intelligence will inevitably explore behaviors we didn't predict or plan for, making perfect guaranteed alignment impossible.

Exactly. One cannot predict the future so ... by doing the diverse ecosystem approach
regarding AIs makes eminent sense. This is akin to the Butterfly Effect whereby the
flapping of a butterfly's wings in Brazil becomes the start point for generating a tornado in Kansas. 

Speaking of math ...

Credit: Image generated by the editorial team using AI for illustrative purposes.

Perfect AI alignment with human values and interests is mathematically impossible, according to a study, but behavioral diversity among AI agents offers the promise of some control. Published in PNAS Nexus, Hector Zenil and colleagues used Gödel's incompleteness theorem and Turing's undecidability result for the Halting Problem to show that any LLM complex enough to exhibit general intelligence or superintelligence will also be computationally irreducible and produce unpredictable behavior, making forced alignment impossible.

The Halting Problem

In computability theory, the halting problem is the decision problem of determining, from a description of an arbitrary computer program and an input, whether the program will eventually halt (finish running) or continue to run forever.[1][2][3] Alan Turing proved in 1936 that the halting problem is undecidable, meaning that no general algorithm exists that can correctly solve the problem for all possible program–input pairs.[4] The problem comes up often in discussions of computability since it demonstrates that some functions are mathematically definable but not computable.

Gödel's Incompleteness theorems

The first incompleteness theorem states that no consistent system of axioms whose theorems can be listed by an effective procedure (i.e. an algorithm) is capable of proving all truths about the arithmetic of natural numbers. For any such consistent formal system, there will always be statements about natural numbers that are true, but that are unprovable within the system. Equivalently, there will always be statements about natural numbers that are false, but that cannot be proved false within the system.

The second incompleteness theorem, an extension of the first, shows
that no such system can demonstrate its own consistency.

To solve the two theorems, one must go outside the system. Hence, OODA

If one looks closely, one sees how to not only solve Gödel's theorems but also
understand how all life uses OODA to cope with the vagaries of reality. :)