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
300
On how various plans miss the hard bits of the alignment challenge
So8res
5mo
81
267
Embedded Agents
abramdemski
4y
41
247
Humans are very reliable agents
alyssavance
6mo
35
202
Embedded Agency (full-text version)
Scott Garrabrant
4y
15
190
Some conceptual alignment research projects
Richard_Ngo
3mo
14
158
Being a Robust Agent
Raemon
4y
32
143
Introduction to Cartesian Frames
Scott Garrabrant
2y
29
135
Demand offsetting
paulfchristiano
1y
38
124
New book on s-risks
Tobias_Baumann
1mo
1
118
Robust Delegation
abramdemski
4y
10
113
Subsystem Alignment
abramdemski
4y
12
107
Our take on CHAI’s research agenda in under 1500 words
Alex Flint
2y
19
105
Embedded World-Models
abramdemski
4y
16
103
The Power of Agency
lukeprog
11y
78
352
EfficientZero: How It Works
1a3orn
1y
42
286
Reward is not the optimization target
TurnTrout
4mo
97
271
Is AI Progress Impossible To Predict?
alyssavance
7mo
38
176
Are wireheads happy?
Scott Alexander
12y
107
129
EfficientZero: human ALE sample-efficiency w/MuZero+self-supervised
gwern
1y
52
115
The Pointers Problem: Human Values Are A Function Of Humans' Latent Variables
johnswentworth
2y
43
109
Will we run out of ML data? Evidence from projecting dataset size trends
Pablo Villalobos
1mo
12
91
When AI solves a game, focus on the game's mechanics, not its theme.
Cleo Nardo
27d
7
80
Jitters No Evidence of Stupidity in RL
1a3orn
1y
18
80
The E-Coli Test for AI Alignment
johnswentworth
4y
24
77
Preface to the sequence on value learning
Rohin Shah
4y
6
75
Seriously, what goes wrong with "reward the agent when it makes you smile"?
TurnTrout
4mo
41
71
RAISE is launching their MVP
3y
1
70
Thoughts on "Human-Compatible"
TurnTrout
3y
35