J Bostock

tl;dr Functional Decision Theory does actually give the right answers. People who construct scenarios where it doesn't, or take umbrage at the idea of "fair problems" are falling foul of symmetry arguments, and would never apply this level of scrutiny to any other system of making decisions. Intro Bentham's Bulldog...

This post was written while working for Arcadia Impact's Alignment Team (and grew out of an internal talk I gave) but is my own opinion and not theirs. I am grateful for feedback from Daniel Tan and the rest of the team. This post was originally going to be more...

Context: We are the ‘model motivations’ team at Arcadia Alignment. We aim to build a science of ‘model intentions’, unifying insights from personas and other empirical evidence. This is an informal research note that has come out of the first 2-3 weeks of exploratory work. In this post, we’ll outline...

“Mode collapse” is a few things. First it was an observation about how early image generating AIs often collapsed to producing just the modal output from their training distribution (something very common, like a house with a white picket fence and a tree in the garden). Then it was the...

TL:DR; or do. I'm a blogpost, not a cop. I'm tired of arguing about AI safety. Not in a pseudo-moralizing "I'm so angry people don't agree with me, let me say that it's tiring" kind of way. I'm simply tired. A couple weeks ago I was at a PauseAI meetup...

Doublehaven remains unaffiliated with Inkhaven 1. Cruel April Two posts per day, for fifteen days. Breeding posts from the dead earth of my drafts, and the recesses of my mind. I would guess a little over twenty thousand words. It was not difficult, just costly. Writing takes time, and time...

The Mirror Test is kind of like Hitler. In any discussion of animal cognition, somebody is going to bring it up. The conversation usually goes like this: > A: So, most animals can’t recognize themselves in the mirror > > B: Which animals specifically? > > A: Oh, dogs, cats,...