Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
73 posts
Reinforcement Learning
Inverse Reinforcement Learning
Wireheading
Reward Functions
Road To AI Safety Excellence
28 posts
AI Capabilities
Definitions
Stag Hunt
Goals
Prompt Engineering
PaLM
EfficientZero
252
Reward is not the optimization target
TurnTrout
4mo
97
167
Are wireheads happy?
Scott Alexander
12y
107
82
Jitters No Evidence of Stupidity in RL
1a3orn
1y
18
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
67
RAISE is launching their MVP
3y
1
63
Thoughts on "Human-Compatible"
TurnTrout
3y
35
59
My take on Michael Littman on "The HCI of HAI"
Alex Flint
1y
4
52
A definition of wireheading
Anja
10y
80
47
Draft papers for REALab and Decoupled Approval on tampering
Jonathan Uesato
2y
2
45
The Stamp Collector
So8res
7y
14
44
You cannot be mistaken about (not) wanting to wirehead
Kaj_Sotala
12y
79
41
Learning biases and rewards simultaneously
Rohin Shah
3y
3
40
A Short Dialogue on the Meaning of Reward Functions
Leon Lang
1mo
0
276
Is AI Progress Impossible To Predict?
alyssavance
7mo
38
273
EfficientZero: How It Works
1a3orn
1y
42
134
EfficientZero: human ALE sample-efficiency w/MuZero+self-supervised
gwern
1y
52
81
When AI solves a game, focus on the game's mechanics, not its theme.
Cleo Nardo
27d
7
74
Will we run out of ML data? Evidence from projecting dataset size trends
Pablo Villalobos
1mo
12
58
Competitive programming with AlphaCode
Algon
10mo
37
51
Misc. questions about EfficientZero
Daniel Kokotajlo
1y
17
40
The Problem With The Current State of AGI Definitions
Yitz
6mo
22
40
Do Humans Want Things?
lukeprog
11y
53
37
Note on Terminology: "Rationality", not "Rationalism"
Vladimir_Nesov
11y
51
34
Remaking EfficientZero (as best I can)
Hoagy
5mo
9
31
Compact vs. Wide Models
Vaniver
4y
5
24
An Agent is a Worldline in Tegmark V
komponisto
4y
12
23
What's the Most Impressive Thing That GPT-4 Could Plausibly Do?
bayesed
3mo
24