Self-improving Artificial Lntelligence and AI Safety
Omohundro started Self-Aware Systems in Palo Alto, California to research the technology and social implications of self-improving artificial intelligence. He was an advisor to the Singularity Institute for Artificial Intelligence and the Lifeboat Foundation on artificial intelligence. He discovered that rational systems exhibit problematic natural "drives" that will need to be countered in order to build intelligent systems safely. His papers, talks, and videos on AI safety have generated extensive interest. He has given many talks on self-improving artificial intelligence, cooperative technology, AI safety, and connections with biological intelligence.
Read more about this topic: Steve Omohundro
Famous quotes containing the words artificial and/or safety:
“Description is revelation. It is not
The thing described, nor false facsimile.
It is an artificial thing that exists,
In its own seeming, plainly visible,
Yet not too closely the double of our lives,
Intenser than any actual life could be....”
—Wallace Stevens (1879–1955)
“Can we not teach children, even as we protect them from victimization, that for them to become victimizers constitutes the greatest peril of all, specifically the sacrifice—physical or psychological—of the well-being of other people? And that destroying the life or safety of other people, through teasing, bullying, hitting or otherwise, “putting them down,” is as destructive to themselves as to their victims.”
—Lewis P. Lipsitt (20th century)