Regularising Utility Functions

I’ve been reading Bostrom’s book Superintelligence recently and one potential solution to some of the problems of accidental unfriendly AI leapt out at me. Bostrom has some pretty silly examples of how encoding utility functions directly into the AI can fail. The most obvious case is the extreme paperclip maximiser... [Read More]

Test first post

Finally started with the website/blog. This is ultimately a test. So see if it works?

What if the UFOs were Aliens

There’s been a lot of hullabaloo about the recent revelations that the Pentagon still has/had a program investigating UFOs and the recently released footage of UFO encounters accompanying it, and furthermore, the suggestion that the aerospace contractor behind it has recovered some actual material from the UFO sites. [Read More]

Friedrich List: Addendums

Although it’s been a while since my last post on List, I recently found a draft of a bunch of relatively disconnected thoughts left over from the earlier post, so I thought I would clean them up and publish them. [Read More]

A Predictive Processing Model of Autism

This is broadly the thesis I have been working on for my dissertation. Now it’s time to start seriously writing up, I thought I’d try writing it down in an informal blog setting first, before translating it into science-ese. [Read More]