Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
180 posts
Research Agendas
Embedded Agency
Suffering
Agency
Animal Welfare
Risks of Astronomical Suffering (S-risks)
Robust Agents
Cause Prioritization
Center on Long-Term Risk (CLR)
80,000 Hours
Crucial Considerations
Veg*nism
164 posts
Value Learning
Reinforcement Learning
AI Capabilities
Inverse Reinforcement Learning
Wireheading
Definitions
Reward Functions
The Pointers Problem
Stag Hunt
Road To AI Safety Excellence
Goals
EfficientZero
258
On how various plans miss the hard bits of the alignment challenge
So8res
5mo
81
248
Humans are very reliable agents
alyssavance
6mo
35
198
Embedded Agents
abramdemski
4y
41
168
Some conceptual alignment research projects
Richard_Ngo
3mo
14
145
Introduction to Cartesian Frames
Scott Garrabrant
2y
29
143
Embedded Agency (full-text version)
Scott Garrabrant
4y
15
131
Demand offsetting
paulfchristiano
1y
38
130
Being a Robust Agent
Raemon
4y
32
112
Our take on CHAI’s research agenda in under 1500 words
Alex Flint
2y
19
110
Robust Delegation
abramdemski
4y
10
103
The Power of Agency
lukeprog
11y
78
100
Subsystem Alignment
abramdemski
4y
12
93
Announcement: AI alignment prize round 3 winners and next round
cousin_it
4y
7
88
"Just Suffer Until It Passes"
lionhearted
4y
26
276
Is AI Progress Impossible To Predict?
alyssavance
7mo
38
273
EfficientZero: How It Works
1a3orn
1y
42
252
Reward is not the optimization target
TurnTrout
4mo
97
167
Are wireheads happy?
Scott Alexander
12y
107
134
EfficientZero: human ALE sample-efficiency w/MuZero+self-supervised
gwern
1y
52
104
The Pointers Problem: Human Values Are A Function Of Humans' Latent Variables
johnswentworth
2y
43
82
Jitters No Evidence of Stupidity in RL
1a3orn
1y
18
81
When AI solves a game, focus on the game's mechanics, not its theme.
Cleo Nardo
27d
7
77
Book Review: Human Compatible
Scott Alexander
2y
6
76
Seriously, what goes wrong with "reward the agent when it makes you smile"?
TurnTrout
4mo
41
76
The Urgent Meta-Ethics of Friendly Artificial Intelligence
lukeprog
11y
252
74
Will we run out of ML data? Evidence from projecting dataset size trends
Pablo Villalobos
1mo
12
69
The E-Coli Test for AI Alignment
johnswentworth
4y
24
68
Preface to the sequence on value learning
Rohin Shah
4y
6