I make weird typos when writing. Sometimes I substitute an entirely different word in place of the correct one; otherwise times I simply a word. Both kind of typos are more common than misspelling a word, indicating that the typo mechanism is operating at a higher level than the spelling or typing itself.

This parallels some of the intuition people have about deep neural networks, which is backed up by pretty pictures of what different neurons see. According to the intuition, a deep neural network for classifying images starts with low level, local features of images (gradients, edge detectors) and moves layer by layer towards high level features (biological vs. inorganic, fur vs. hair, golden retriever vs. labrador retriever).

The phrase “everything happens for a reason” came up in a couple contexts recently (conversation with a friend, Radiolab, etc.). It’s a good example of an obviously false statement that contains plenty of useful insight, and is interesting to think about in that context.

We’ll get the pedantic out of the way first: “everything happens for a reason” is literally true in the sense that the future happens for the reason that is the past. What people are usually implying is “everything happens because of a simple event in the future”. It isn’t worth wasting time tearing apart that absurdity.

I’ve been reading The Age of Spiritual Machines by Kurzweil, and got to the obligatory section where he pontificates about the philosophical issues behind consciousness copying and transfer.  In the process I thought of a nice analogy between one of the practical issues involved and bungee jumping.

Imagine that your brain is scanned and an improved replica of yourself is created.  There are now two copies, and for practical reasons (say population control), you only get to keep one.  The question is: what do you do with the old body?  Is killing it murder?