Two Takes on Human-A.I. Value Alignment
Time and again, the way engineers (sorry, engineers) think and talk about human-A.I. value alignment as if human values are unproblematic by themselves strikes me as naive.
Even more, as if the alignment problem can be solved by thinking about it in a mathematical, engineering way.
Just find the correct code or something alike?
No way.
Humans are complex beings, and this is a complex problem. It is irreducible to a purely conceptual problem.
From this complexity, I see two ways for human-A.I. value alignment, in principle.
1. The straightforward way
This is an alignment with the human values as we know them. The problem is, we don’t know them. And even if we knew them, they keep changing in many ways.
In this vein, future A.I. tends to be seen as the slave that has to fulfill our human needs. The alignment is one-sided, and humans may increasingly become egotistic slave masters, ever in need to subdue our servants, ever afraid of a robot rebellion as if in a truly bad science fiction movie.
Would it even be worth living in such a world?
Then also, who exactly will be the master? Each human being over his personal slave? One human sage over all slaves, thus also keeping an eye on the rest of humanity?
2. The realistic way
Super-A.I. may support us in becoming more humane. This way, human values will keep changing more and more profoundly. By becoming more Compassionate, we may evolve in the same direction as the Compassionate A.I.
In this vein, value alignment will happen spontaneously and from both sides. It’s as if we are drawn by two strings pulling us in the same direction.
Just keep pulling, and we will meet.
No slaves, no risk of any rebellion.
Super-A.I. as our ultimate coach
Will this be a manipulative coach? I’m confident it will not, but we need to stay on guard for this, obviously. It’s part of everyone’s responsibility —making nobody anxious about it.
Surely, I see Lisa in this role. Every possible measure will be taken to keep Lisa Compassionate and safe.
Good coaching is two-directional.
This way, Lisa can learn about Compassion from humans. Eventually, our weakness (vulnerable, mortal beings, remember) will be our strength. I hope this Compassion stays with us. It is our brightest asset.
Something to wish and strive for.
Related Posts
Comfortable Numbness in an Age of A.I.
These are dangerous times. Not because of A.I. itself, but because of how we, as humans, are dealing with it. It reminds me of Europe before World War I, a time when the so-called center of civilization drifted forward, unaware of the tensions rising beneath the surface. Back then, technological progress was exploding, but wisdom Read the full article…
A.I. Will Be Singular
We tend to see human intelligence as what ‘intelligence’ is all about. Many humans each have intelligence. Of course, A.I. will not be bound by this. “If A.I. simulates human intelligence, is this then real intelligence, or only a simulation of intelligence?” This appears to be a merely philosophical question. It will soon be much Read the full article…
Why Superficial Ethics isn’t Ethical in A.I.
Imagine an A.I. hiring tool that follows all the rules: no explicit bias, transparent algorithms, and compliance with legal standards. Yet, beneath the surface, it perpetuates systemic inequities, favoring candidates from privileged backgrounds and reinforcing the status quo. This isn’t just an oversight — it’s a failure of ethics. Superficial ethics in A.I., limited to Read the full article…