AI ALIGNMENT FORUM
AF

631
Stuff I found online

Stuff I found online

Jan 31, 2023 by the gears to ascension

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

0the gears to ascenscion's Shortform
the gears to ascension
2y
0
5[paper link] Interpreting systems as solving POMDPs: a step towards a formal understanding of agency
the gears to ascension
3y
0
3Relevant to natural abstractions: Euclidean Symmetry Equivariant Machine Learning -- Overview, Applications, and Open Questions
the gears to ascension
3y
0
0[link, 2019] AI paradigm: interactive learning from unlabeled instructions
the gears to ascension
3y
0
3Metaphor.systems
the gears to ascension
3y
0
-3Stop Talking to Each Other and Start Buying Things: Three Decades of Survival in the Desert of Social Media
the gears to ascension
3y
0
11Call for submissions: “(In)human Values and Artificial Agency”, ALIFE 2023
the gears to ascension
3y
0
4Hinton: "mortal" efficient analog hardware may be learned-in-place, uncopyable
the gears to ascension
3y
0
5Hunch seeds: Info bio
the gears to ascension
3y
0
12How to Read Papers Efficiently: Fast-then-Slow Three pass method
the gears to ascension, 1stuserhere, lastuserhere
3y
0
23A bunch of videos for intuition building (2x speed, skip ones that bore you)
the gears to ascension
3y
0
9Found Paper: "FDT in an evolutionary environment"
the gears to ascension
2y
0
1A bunch of videos in comments
the gears to ascension
2y
0
2gamers beware: modded Minecraft has new malware
the gears to ascension
2y
0
11"Benevolent [ie, Ruler] AI is a bad idea" and a suggested alternative (not author)
the gears to ascension
2y
0
4[via bsky, found paper] "AI Consciousness: A Centrist Manifesto"
the gears to ascension
1mo
0