Stuff I found online

A series of posts of stuff I found online that didn’t seem well enough known in the inter-agency safety/​ai safety community.

the gears to as­cen­scion’s Shortform

In­ter­pret­ing sys­tems as solv­ing POMDPs: a step to­wards a for­mal un­der­stand­ing of agency [pa­per link]

Rele­vant to nat­u­ral ab­strac­tions: Eu­clidean Sym­me­try Equiv­ar­i­ant Ma­chine Learn­ing—Overview, Ap­pli­ca­tions, and Open Questions

[link, 2019] AI paradigm: in­ter­ac­tive learn­ing from un­la­beled instructions

Me­taphor.systems

Stop Talk­ing to Each Other and Start Buy­ing Things: Three Decades of Sur­vival in the Desert of So­cial Media

[talk] Os­bert Bas­tani—In­ter­pretable Ma­chine Learn­ing via Pro­gram Syn­the­sis—IPAM at UCLA

Call for sub­mis­sions: “(In)hu­man Values and Ar­tifi­cial Agency”, ALIFE 2023

Hin­ton: “mor­tal” effi­cient ana­log hard­ware may be learned-in-place, uncopyable

Hunch seeds: Info bio

How to Read Papers Effi­ciently: Fast-then-Slow Three pass method

A bunch of videos for in­tu­ition build­ing (2x speed, skip ones that bore you)