Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
41 posts
Reinforcement Learning
AI Capabilities
Wireheading
Reward Functions
EfficientZero
Tradeoffs
33 posts
Embedded Agency
Subagents
Robust Agents
Category Theory
Spurious Counterfactuals
Memetics
Autonomous Vehicles
7
Note on algorithms with multiple trained components
Steven Byrnes
7h
1
104
Will we run out of ML data? Evidence from projecting dataset size trends
Pablo Villalobos
1mo
12
271
Reward is not the optimization target
TurnTrout
4mo
97
43
A Short Dialogue on the Meaning of Reward Functions
Leon Lang
1mo
0
89
Scaling Laws for Reward Model Overoptimization
leogao
2mo
11
107
Evaluations project @ ARC is hiring a researcher and a webdev/engineer
Beth Barnes
3mo
7
334
EfficientZero: How It Works
1a3orn
1y
42
61
Towards deconfusing wireheading and reward maximization
leogao
3mo
7
42
Four usages of "loss" in AI
TurnTrout
2mo
18
72
Seriously, what goes wrong with "reward the agent when it makes you smile"?
TurnTrout
4mo
41
120
We have achieved Noob Gains in AI
phdead
7mo
21
32
It matters when the first sharp left turn happens
Adam Jermyn
2mo
9
124
EfficientZero: human ALE sample-efficiency w/MuZero+self-supervised
gwern
1y
52
43
Remaking EfficientZero (as best I can)
Hoagy
5mo
9
237
Humans are very reliable agents
alyssavance
6mo
35
43
Gradations of Agency
Daniel Kokotajlo
7mo
6
107
Reward Is Not Enough
Steven Byrnes
1y
18
135
Introduction to Cartesian Frames
Scott Garrabrant
2y
29
24
You Only Get One Shot: an Intuition Pump for Embedded Agency
Oliver Sourbut
6mo
4
188
Why Subagents?
johnswentworth
3y
42
191
Embedded Agency (full-text version)
Scott Garrabrant
4y
15
111
Robust Delegation
abramdemski
4y
10
52
Additive Operations on Cartesian Frames
Scott Garrabrant
2y
6
107
Subsystem Alignment
abramdemski
4y
12
53
Updates and additions to "Embedded Agency"
Rob Bensinger
2y
1
47
Subagents of Cartesian Frames
Scott Garrabrant
2y
5
99
Embedded World-Models
abramdemski
4y
16
96
Embedded Curiosities
Scott Garrabrant
4y
1