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
Will Super-A.I. Make People Happier?
This is the paramount question — more vital than any debate about intelligence. It’s a bit weird that it is seldom put at the forefront, as if we’re more concerned about who is the most knowledgeable, therefore the most powerful. What people? It should not be about a few, as it should not exclude billions. Read the full article…
What Ethical A.I. is (Not)
There’s a growing urgency around how we shape the future of artificial intelligence. More and more, we hear about ‘ethical A.I.’ — systems that behave nicely, avoid harm, and follow rules. But let’s pause. Is that really what ethics means? And more importantly, is that all it can be? Please first read this blog: What Read the full article…
Trustworthy A.I.: Not Explainable, but Aligned
Trust in A.I. is often discussed as if it were merely a matter of clear rules and transparent explanations. Yet both humans and super-A.I. are far too complex for that ideal. Full explainability is an illusion. What can make A.I. truly trustworthy is alignment with Compassion, a living compass that adapts as life unfolds. This Read the full article…