LESSWRONG
LW

The Ethicophysics

Nov 30, 2023 by MadHatter

In this sequence, we attempt to solve the alignment problem, rather than discussing it ad infinitum. Since the alignment problem is incredibly difficult to solve, this sequence is probably going to end up being pretty long, and many of the posts will be more complex and harder to read than they really have to be. We apologize to the reader for this situation, and promise to improve the individual posts and the overall flow of the sequence as quickly as our limited time permits.

149Moral Reality Check (a short story)
jessicata
2y
45
82Agent Boundaries Aren't Markov Blankets. [Unless they're non-causal; see comments.]
Ω
abramdemski
2y
Ω
11
-13My Alignment Research Agenda ("the Ethicophysics")
MadHatter
2y
0
2Some Intuitions for the Ethicophysics
MadHatter, mishka
2y
4
-19The Alignment Agenda THEY Don't Want You to Know About
MadHatter
2y
16
8My Mental Model of Infohazards
MadHatter
2y
34
31Stupid Question: Why am I getting consistently downvoted?
Q
MadHatter, Shankar Sivarajan
2y
Q
138
95Trying to Make a Treacherous Mesa-Optimizer
Ω
MadHatter
3y
Ω
14
-45Homework Answer: Glicko Ratings for War
MadHatter
2y
1
-15Enkrateia: a safe model-based reinforcement learning algorithm
MadHatter
2y
4
-22A Formula for Violence (and Its Antidote)
MadHatter
2y
6