I am so glad that this was written. I’ve been giving similar advice to people, though I have never articulated it this well. I’ve also been giving this advice to myself, since for the past two years I’ve spent most of my time doing “duty” instead of play, and I’ve seen how that has eroded my productivity and epistemics. For about six months, though, beginning right after I learned of GPT-3 and decided to dedicate the rest of my life to the alignment problem, I followed the gradients of fun, or as you so beautifully put it, thoughts that are led to exuberantly play themselves out, a process I wrote about in the Testimony of a Cyborg appendix of the Cyborgism post. What I have done for fun is largely the source of what makes me useful as an alignment researcher, especially in terms of comparative advantage (e.g. decorrelation, immunity to brainworms, ontologies shaped/nurtured by naturalistic exploration, (decorrelated) procedural knowledge).
The section on “Highly theoretical justifications for having fun” is my favorite part of this post. There is so much wisdom packed in there. Reading this section, I felt that a metacognitive model that I know to be very important but have been unable to communicate legibly has finally been spelled out clearly and forcefully. It’s a wonderful feeling.
I expect I’ll be sending this post, or at least that section, to many people (the whole post is a long and meandering, which I enjoyed, but it’s easier to get someone to read something compressed and straight-to-the-point).
I am so glad that this was written. I’ve been giving similar advice to people, though I have never articulated it this well. I’ve also been giving this advice to myself, since for the past two years I’ve spent most of my time doing “duty” instead of play, and I’ve seen how that has eroded my productivity and epistemics. For about six months, though, beginning right after I learned of GPT-3 and decided to dedicate the rest of my life to the alignment problem, I followed the gradients of fun, or as you so beautifully put it, thoughts that are led to exuberantly play themselves out, a process I wrote about in the Testimony of a Cyborg appendix of the Cyborgism post. What I have done for fun is largely the source of what makes me useful as an alignment researcher, especially in terms of comparative advantage (e.g. decorrelation, immunity to brainworms, ontologies shaped/nurtured by naturalistic exploration, (decorrelated) procedural knowledge).
The section on “Highly theoretical justifications for having fun” is my favorite part of this post. There is so much wisdom packed in there. Reading this section, I felt that a metacognitive model that I know to be very important but have been unable to communicate legibly has finally been spelled out clearly and forcefully. It’s a wonderful feeling.
I expect I’ll be sending this post, or at least that section, to many people (the whole post is a long and meandering, which I enjoyed, but it’s easier to get someone to read something compressed and straight-to-the-point).
Thanks.
Nice!