AI Alignment vs 'The Invisible Hand'



AI Alignment is defined as "the field of research/engineering dedicated to ensuring that AI systems act in accordance with human intentions, values, and ethical principles".

And to understand this issue at a deeper level, we need to understand how humans act in accordance with intentions, values, and ethical principles. And, in my opinion, we don't... or more accurately, we do not act with intention to ethically act.

Humans act selfishly, as all animals do. The difference in intelligent species is that our selfish acts are governed by the 'invisible hand' as outlined by Adam Smith in 1776 in his Wealth of Nations. The invisible hand is thus loosely defined as: where the individual selfish act (generally) results in a net benefit to society, when there was no intention to do so.

A simple example is our own survival. We selfishly act to continue to live, yet we implicitly understand that we should not end the lives of others, as they could do the same to us. This unspoken societal 'restriction' is an unintended result of our selfish acts/thoughts.

Societal morality is the same logic. We generally act, governed by an invisible hand, within a bell-curve of possible actions which have been 'accepted' by the majority of society. So the invisible hand becomes... I won't act this way because I don't want anyone else to act this way. It's a form of empathy, not a personal one, but for society itself.

Thus alignment cannot be a set of rules, as intentions, values, and ethical principles are just points-in-time within the ever-changing morass of societal subjective opinions governed by the invisible hand.

So the question for AI alignment becomes: how do we instil within AI this 'invisible hand'?

And I think it is impossible. We implicitly 'behave' because society has penalties for acting in a non-behaving manner. Either hard penalties such as fines, or imprisonment. Or softer penalties such as shaming/ridicule and isolation.

What are such penalties to an AI engine? Or, more accurately, what penalties would 'matter' to an AI engine?

We can't tell AI to 'go to your room without dinner'... or can we?

Comments

Post a Comment

Popular posts from this blog

The power of nOne Nails

Image
As you can see, there are 2 Nails on this blog-post to the right. Click on them. See what they do. Nails are the visible component of the nOne ecosystem. A metaphor for Nails is that they are nails to drive into the ground of the digital realm announcing, to the world, that you want to be respected by the engines/platforms/algorithms/automation/etc, and here are my required permissions relating to this external functionality. So now an AI Crawler can find this page with my 2 Nails. Grab my preferences, and respect them. I will be using this blogpost as a demo of how the current AI engines can be controlled at the execution layer once the authoritative constraints are recognised. We hope that the digital ground will be covered with these Nails forming the base framework of the layer of permissions which must be respected by the various platforms. Nails can be visible on every blog-post, web-page, and email (add to your signature). /* Sample .none file */ Email:   allowPromotionalCon...
Read more

AI Governance - The Trolley Problem

Image
Wrt AI governance, let's talk how we govern subjective human beings. In the hunter/gatherers era, we would kick a renegade person out of the tribe/village/etc, which may mean certain death at the hands of predators/enemy tribes/etc. Later in our evolution, we created deities along with a set of divine laws, where the offender would pay a penalty for their misdeeds in the after life (as there were no police forces at that time). Now we have a criminal code which does not stop the person from behaving outside the 'norms', but if caught, results in increasingly severe penalties for acting in breach of those laws. All of these measures are reactive... because humans are subjective. We cannot impose proactive rules that limit how we act because a) that would create a society of robots, and b) a human could act in a manner which has not even been considered by the creators of the laws. This is why we have courts, which take the individual circumstances of their subjective actions...
Read more

nOne – An Overview - 042026

Image
Look at the 2 nOne Nails above-right. Click on them. See what they do. This is the visual nOne.  nOne is the first subjective layer of the Internet.  The vision of nOne is to mirror within the digital realm with what we currently have in the social realm. All social interactions come from a base of permissions and consent, whether this is implicit or explicit. We stick out our hand to shake the hand of another, and all this is implicitly governed by permissions and consent. Action must respect permission. In fact, it is not a stretch to say that activities within the social realm which do not respect permissions are illegal. We must have an equal system of respect within the digital realm.  However, this is not how our existing digital realm operates. Currently, it is the engines/platforms/algorithms which hold ownership over us, held captive by the 8-screen EULA. AI Crawlers use our content/IP for training, platforms contain behavioural automation to keep us captive and...
Read more