Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
13 posts
AI Capabilities
EfficientZero
15 posts
Definitions
Stag Hunt
Goals
Prompt Engineering
PaLM
71
When AI solves a game, focus on the game's mechanics, not its theme.
Cleo Nardo
27d
7
39
Will we run out of ML data? Evidence from projecting dataset size trends
Pablo Villalobos
1mo
12
281
Is AI Progress Impossible To Predict?
alyssavance
7mo
38
10
Can GPT-3 Write Contra Dances?
jefftk
16d
0
194
EfficientZero: How It Works
1a3orn
1y
42
5
Mastering Stratego (Deepmind)
svemirski
18d
0
139
EfficientZero: human ALE sample-efficiency w/MuZero+self-supervised
gwern
1y
52
69
Misc. questions about EfficientZero
Daniel Kokotajlo
1y
17
51
Competitive programming with AlphaCode
Algon
10mo
37
23
Remaking EfficientZero (as best I can)
Hoagy
5mo
9
11
What's the Most Impressive Thing That GPT-4 Could Plausibly Do?
bayesed
3mo
24
2
How might we make better use of AI capabilities research for alignment purposes?
ghostwheel
3mo
4
2
Uncompetitive programming with GPT-3
Bezzi
10mo
8
35
The Problem With The Current State of AGI Definitions
Yitz
6mo
22
20
What Belongs in my Glossary?
Zvi
2y
8
44
Compact vs. Wide Models
Vaniver
4y
5
39
An Agent is a Worldline in Tegmark V
komponisto
4y
12
29
Disambiguating "alignment" and related notions
David Scott Krueger (formerly: capybaralet)
4y
21
50
Do Humans Want Things?
lukeprog
11y
53
43
Note on Terminology: "Rationality", not "Rationalism"
Vladimir_Nesov
11y
51
19
Seeking better name for "Effective Egoism"
DataPacRat
6y
30
9
What's in a name? That which we call a rationalist…
badger
13y
92
8
ESR's comments on some EY:OB/LW posts
Eliezer Yudkowsky
13y
16
6
Beginning at the Beginning
Annoyance
13y
60
1
Define Rationality
Marshall
13y
14
0
The two meanings of mathematical terms
JamesCole
13y
80
-2
Glossary of Futurology
mind_bomber
7y
7