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
The Learning Landscape: A Flexible View of Machine Learning
Machine learning is often divided into neatly defined categories: supervised, unsupervised, semi-supervised, and reinforcement learning. In reality, learning – whether in machines or humans – functions more like a fluid landscape, where different approaches blend and interact. In this blog, we’ll explore the concept of the ‘learning landscape,’ where traditional types of machine learning are Read the full article…
Lessons from OOA&D for present-day A.I.
Present-day A.I. is rediscovering challenges that software engineering already faced decades ago. Object-oriented analysis and design (OOA&D) offered powerful answers, yet also revealed clear limits. By revisiting these lessons with today’s understanding, we can see where the line was interrupted — and how it can be continued. This blog explores what OOA&D still teaches us, Read the full article…
Parallel Humans ― Serial A.I.
Before diving into this blog, I recommend first reading Coarse Comparison of Brain and Silicon to grasp the foundational distinctions between human and silicon-based processing. This continuation focuses on the profound differences between the parallelism of GPUs and the parallelism of the human brain. Here, we explore what these differences mean for intelligence and its Read the full article…