[Question] What are the best published papers from outside the alignment community that are relevant to Agent Foundations?

[Stephen Fowler]

I am after papers that you have stumbled across that may be relevant to the core of the understanding the existential AI alignment problem despite not having explicit links to AI alignment.

Here are papers I have found that fit the above criteria to give you a better idea of what I’m after:

• Primas, Hans. Emergence in Exact Natural Science. 1998

• Shalizi, Cosma. Causal Architecture, Complexity, and Self-Organization in Time Series and Cellular Automata. 2001

• Jeremy, England. Dissipative Adaptation in Driven Self-Assembly. 2015

While I’ve used the term “agent foundations” I expect the majority of useful papers will not use terms like agency, optimization etc.

[rorygreig]

An interesting paper is The information theory of individuality, Krakauer et. al

[Martín Soto]

Maybe Computationally Tractable Choice.

[martin biehl]

Interpreting Systems as Solving POMDPs: A Step Towards a Formal Understanding of Agency

https://​​link.springer.com/​​chapter/​​10.1007/​​978-3-031-28719-0_2

[Roman Leventov]

“General cognitive science”: Boyd et al. (2022), Goyal & Bengio (2022), Levin (2022), Fields et al. (2022), Friston et al. (2022), Ma et al. (2022), LeCun (2022) (links from here).

Also, general theories of cognitive development, e.g., Kuchling et al. 2022; Fields et al. 2022.