About Me

I’m a technologist and generally curious person. I often go down rabbit holes and spend days or weeks on a topic or trying to answer a question. I created this website as another outlet for my curiousity.

Recently, I’ve had a growing interest in the field of AI safety and alignment.

To motivate this interest, consider the following quote by Nick Bostrom from his paper, The Vulnerable World Hypothesis:

“One way of looking at human creativity is as a process of pulling balls out of a giant urn. The balls represent possible ideas, discoveries, technological inventions… What we haven’t extracted, so far, is a black ball: a technology that invariably or by default destroys the civilization that invents it.”

Is AI a black ball? I really think it could be. Ultimately, the jury is still out and the decisions the people building this technology make today will give this ball its final color. Consider though, that frontier models have been improving quickly, and it no longer feels like science fiction to say that we will find out very soon.

With that thought in mind, I plan on launching this site around this topic to start, and writing about what researchers are doing to make the technology safe, what gaps exist still, and maybe, just maybe, to contribute research directly if I can.

It will be a long hill to climb - I haven’t inverted a matrix or calculated a derivative in over 10 years. So, I figure why not document the steps along the way? Maybe someone else in a similar situation will find something on here useful.