AI ALIGNMENT FORUM
AF

Wikitags

AI Alignment Intro Materials

Edited by Raemon, Ruby, plex, et al. last updated 30th Dec 2024

AI Alignment Intro Materials are posts that help someone get oriented and skill up. Distinct from AI Public Materials is that they are more "inward facing" than "outward facing", i.e. for people who are already sold AI risk is a problem and want to upskill.
 

Some basic intro resources include:

  • Stampy's AI Safety Info (extensive interactive FAQ)
  • Scott Alexander's Superintelligence FAQ
  • The MIRI Intelligence Explosion FAQ
  • The AGI Safety Fundamentals courses
  • Superintelligence (book)
Subscribe
2
Subscribe
2
Discussion0
Discussion0
Posts tagged AI Alignment Intro Materials
35The Alignment Problem from a Deep Learning Perspective (major rewrite)
SoerenMind, Richard_Ngo, LawrenceC
3y
2
6"Corrigibility at some small length" by dath ilan
Christopher King
2y
1
12A newcomer’s guide to the technical AI safety field
zeshen
3y
1
102AI Control: Improving Safety Despite Intentional Subversion
Buck, Fabien Roger, ryan_greenblatt, Kshitij Sachan
2y
5
48A short course on AGI safety from the GDM Alignment team
Vika, Rohin Shah
7mo
0
23Wikipedia as an introduction to the alignment problem
SoerenMind
2y
0
26A starter guide for evals
Marius Hobbhahn, Jérémy Scheurer, Mikita Balesni, rusheb, AlexMeinke
2y
0
17UC Berkeley course on LLMs and ML Safety
Dan H
1y
1
72Shallow review of technical AI safety, 2024
technicalities, Stag, Stephen McAleese, jordine, Dr. David Mathers
8mo
1
23An Exercise to Build Intuitions on AGI Risk
Lauro Langosco
2y
3
Add Posts