With the sudden simultaneous exits of Mira Murati, Barret Zoph, and Bob McGrew, I thought I'd update my tally of the departures from OpenAI, collated with how quickly the ex-employee had signed the loyalty letter to Sam Altman last November.
The letter was leaked at 505 signatures, 667 signatures, and finally 702 signatures; in the end, it was reported that 737 of 770 employees signed. Since then, I've been able to verify 56 departures of people who were full-time employees (as far as I can tell, contractors were not allowed to sign, but all FTEs were).
I still think I'm missing some, so these are lower bounds (modulo any mistakes I've made).
Headline numbers:
Reportedly, 737 out of the 770 signed in the end, and many of the Superalignment team chose not to sign at all.
Below are my current tallies of some notable subsets. Please comment with any corrections!
People from the Superalignment team who never signed as of the 702 leak (including some policy/governance people who seem to have been closely connected) and are now gone:
People from the Superalignment team (and close collaborators) who did sign before the final leak but are now gone:
Others who didn't sign as of the 702 leak (some of whom may have just been AFK for the wrong weekend, though I doubt that was true of Karpathy) and are now gone:
Notable other ex-employees:
How do you formalize the definition of a decision-theoretically fair problem, even when abstracting away the definition of an agent as well as embedded agency?
I've failed to find anything in our literature.
It's simple to define a fair environment, given those abstractions: a function E from an array of actions to an array of payoffs, with no reference to any other details of the non-embedded agents that took those actions and received those payoffs.
However, fair problems are more than just fair environments: we want a definition of a fair problem (and fair agents) under which, among other things:
Modal combat doesn't need to worry about this, because all the agents in it are fair-by-construction.
Yeah, I know, it's about a decade late to be asking this question.
It's an essential aspect of decision making for an agent to figure out where it might be. Thought experiments try to declare the current situation, but they don't necessarily need to be able to convincingly succeed. Algorithmic induction, such as updating from Solomonoff prior, is the basic way an agent figures out which situations it should care about, and declaring that we are working with a particular thought experiment doesn't affect the prior. In line with updatelessness, an agent should be ready for observations in general (according to which of them it cares about more), rather than particular "fair" observations, so distinguishing observations that describe "fair" thought experiments doesn't seem right either.
My current candidate definitions, with some significant issues in the footnotes:
A fair environment is a probabilistic function from an array of actions to an array of payoffs.
An agent is a random variable
which takes in a fair environment [1] and a list of agents (including itself), and outputs a mixed strategy over its available actions in . [2]
A fair agent is one whose mixed strategy is a function of subjective probabilities[3] that it assigns to [the actions of some finite collection of agents in fair environments, where any agents not appearing in the original problem must themselves be fair].
Formally, if is a fair agent in with a subjective probability estimator , 's mixed strategy in a fair environment ,
should depend only on a finite collection of 's subjective probabilities about outcomes
for a set of fair environments and an additional set of fair[4] agents[5] if needed (note that not all agents need to appear in all environments).
A fair problem is a fair environment with one designated player, where all other agents are fair agents.
I might need to require every to have a default action , so that I don't need to worry about axiom-of-choice issues when defining an agent over the space of all fair environments.
I specified a probabilistic environment and mixed strategies because I think there should be a unique fixed point for agents, such that this is well-defined for any fair environment . (By analogy to reflective oracles.) But I might be wrong, or I might need further restrictions on .
Grossly underspecified. What kinds of properties are required for subjective probabilities here? You can obviously cheat by writing BlueEyedBot into your probability estimator.
This is an infinite recursion, of course. It works if we require each to have a strictly lower complexity in some sense than (e.g. the rank of an agent is the largest number of environments it can reason about when making any decision, and each needs to be lower-rank than ), but I worry that's too strong of a restriction and would exclude some well-definable and interesting agents.
Does the fairness requirement on the suffice to avert the MetaBlueEyedBot problem in general? I'm unsure.