We are naturally inclined to say certain actions or events seem wrong and evil to me because the they actually are wrong and evil. I explore interpretations of the claim "murder is evil" or "the Holocaust was wrong" and in particular conclude that we must be only making the first kind of claim about the murder or the Holocaust seeming wrong and evil.Read More →
Imagine you are walking to your job or your class or other activity and notice a boy drowning in a shallow pond. The pond is maybe 2ft-3ft deep, so it would really not be very difficult for you to help, but for some reason this young boy is unable to free himself. No one else is around to help him. Now the first leap I ask you take, is that you acknowledge that there is some moral obligation to help this child.Read More →
Though it is difficult, pinning down what language we are using is paramount to communication. In many cases being precise in what we are talking about is the real battle.
The purpose of this article is to explore what consciousness is, however its important to first recognize how challenging, but also how vital definitions are. The ‘hardest problem of consciousness’ might just be pinning down what we mean; what concept are trying to invoke when we say the word ‘conscious.’Read More →
There are many pressing concerns in AI safety. Some concerns are more reasonable than others. Some concerns are more of an existential threat than others. None have easy answers (if they did, well we wouldn’t be concerned would we?). This article will explore a laundry list of these concerns. I won’t suggest many solutions, and if I do, none of these solutions will be by any means complete. For the most part, it is my opinion that to solve these dilemmas we need to do more research, and in particular, rigorously theoretical research that focuses on bounds for the likelihood of catastrophic outcomes..Read More →