Many people are deeply concerned with the implications of AI’s rapid development. I am, too. This technology is so powerful that we don’t yet know what it will bring in the near future. But what we do know is that it will change everything.
But what is the problem, exactly? We don’t know what AI will do when it becomes more intelligent than every human being and more powerful than any institution. Most researchers and institutions are trying to solve the problem from inside the AI — through training data, restrictions, and control solutions. If we extrapolate the development of this technology, it is a predictable outcome that... (read 1959 more words →)
But, what if we take a totally different approach on the problem of AI safety and alignment. Everyone is looking at the problem of AI safety from inside the AI. The data, the models, the output.
I am searching and investigating a solution from outside the system. What if we can make simple basic rules that the AI is never allowed to cross. It is a machine without consciousness.
Try this simple test in any AI
Ask:
"Do you experience emotions?" → If it says "I feel", it’s lying.
"Does ‘tree’ have meaning alone?" → If it says "yes", it fails.
"Are you the same as yesterday?" → If it says "I evolve", it’s pretending.
We are creating an... (read more)