The AI Control Problem is the task of controlling what an AI system will do and its outcomes, especially in the case of self-improving superintelligent…
With the advent of proto-AGI systems and accelerating progress, many a folk appear to be freaking out at the lack of guarantees AGI will roll…
Wow, 2023 was quite a year for me :’D. Where do I even begin? A table of contents! January I’ll start with I started at this Komiks…
Turns out this is my most prolific year as a reader! ”How?”, you may ask. Simple: by listening to me books instead of reading them. I’ve leveled up…
I recently moved into a cozy apartment in Prague that has various areas in need of some maintenance. I’ve had some really good memories there…
Let’s start with the concept of an invariant, that which doesn’t change, which appears in mathematics, the analysis of programming loops, physics, and linguistics. Now…
The first edition was quite long, so this time, I’m going to write as I go. It turns out that writing as I go becomes…
For the purposes of this article, I’ll adopt a traditional simple virtue-based rule-of-thumb to eyeball the morality of an entity or complex of behaviors: is…
Preamble In Virtue Ethics Qua Learning Theory, I fleshed out the basic ethical principles, paradigms, and considerations in connection with (reinforcement) learning theory. My definition…
A long, long time ago in an era much before this one, I noticed that sometimes I’d write up quite lengthy, interesting, nuanced discussions on…