AI Alignment MOC

up:: Interests

What are AI

There are two kinds of AI: Narrow AI and Artificial General Intelligence (AGI)

How do machines learn

Machine learning uses data to answer questions. An agent gets trained (uses data) to make predictions (answers questions).

Problems: AI Alignment Theory

The real risk with AI isn’t malice but competence. A super-intelligent AI will be extremely good at accomplishing its goals, and if those goals aren’t aligned with ours we’re in trouble. – Stephen Hawking

Utility Functions

Problems with AI

AI and human society

Important Players

DeepMind TK

source: Computerphile YouTube playlist on AI

Unreturned links

These notes point towards this note. But this note doesn’t point back.


TABLE file.mtime.year + ”-” + file.mtime.month + ”-” + AS Modified FROM AI Safety MOC and !outgoing(AI Safety MOC) SORT file.mtime desc