[mathjax] Decision theory and artificial intelligence typically try to compute something resembling $$\underset{a \ \in \ Actions}{\mathrm{argmax}} \ \ f(a).$$ I.e., maximize some function of the action. This tends to assume that we can detangle things enough to see...
[mathjax] Suppose you want to build a robot to achieve some real-world goal for you—a goal that requires the robot to learn for itself and figure out a lot of things that you don’t already know. ((This is part...
The following is a fictional dialogue building off of AI Alignment: Why It’s Hard, and Where to Start. (Somewhere in a not-very-near neighboring world, where science took a very different course…) ALFONSO: Hello, Beth. I’ve noticed a lot of...
[mathjax] The following is a basically unedited summary I wrote up on March 16 of my take on Paul Christiano’s AGI alignment approach (described in “ALBA” and “Iterated Distillation and Amplification”). Where Paul had comments and replies, I’ve included them...
This is a reply to Francois Chollet, the inventor of the Keras wrapper for the Tensorflow and Theano deep learning systems, on his essay “The impossibility of intelligence explosion.” In response to critics of his essay, Chollet tweeted: If...
Follow-up to: Security Mindset and Ordinary Paranoia (Two days later, Amber returns with another question.) AMBER: Uh, say, Coral. How important is security mindset when you’re building a whole new kind of system—say, one subject to potentially adverse optimization pressures,...
