Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
39 posts
Language Models
Scaling Laws
Definitions
PaLM
Prompt Engineering
Robotics
Exploratory Engineering
Simulacrum Levels
16 posts
Agency
Deconfusion
Tool AI
Simulation Hypothesis
Philosophy of Language
Astronomical Waste
Carving / Clustering Reality
28
Discovering Language Model Behaviors with Model-Written Evaluations
evhub
4h
3
27
Take 11: "Aligning language models" should be weirder.
Charlie Steiner
2d
0
234
chinchilla's wild implications
nostalgebraist
4mo
114
163
Language models seem to be much better than humans at next-token prediction
Buck
4mo
56
75
Inverse Scaling Prize: Round 1 Winners
Ethan Perez
2mo
16
28
Inverse scaling can become U-shaped
Edouard Harris
1mo
15
141
Announcing the Inverse Scaling Prize ($250k Prize Pool)
Ethan Perez
5mo
14
45
Smoke without fire is scary
Adam Jermyn
2mo
22
99
Help ARC evaluate capabilities of current language models (still need people)
Beth Barnes
5mo
6
40
Paper: Large Language Models Can Self-improve [Linkpost]
Evan R. Murphy
2mo
14
113
The case for becoming a black-box investigator of language models
Buck
7mo
19
84
Who models the models that model models? An exploration of GPT-3's in-context model fitting ability
Lovre
6mo
14
157
Transformer Circuits
evhub
12mo
4
106
Testing PaLM prompts on GPT3
Yitz
8mo
15
185
Simulators
janus
3mo
103
56
LOVE in a simbox is all you need
jacob_cannell
2mo
69
63
Vingean Agency
abramdemski
3mo
13
33
Discovering Agents
zac_kenton
4mo
8
33
Why agents are powerful
Daniel Kokotajlo
6mo
7
27
[Intro to brain-like-AGI safety] 11. Safety ≠ alignment (but they’re close!)
Steven Byrnes
8mo
1
24
Some reasons why a predictor wants to be a consequentialist
Lauro Langosco
8mo
16
48
Looking Deeper at Deconfusion
adamShimi
1y
13
24
Agency: What it is and why it matters
Daniel Kokotajlo
1y
2
38
Beware over-use of the agent model
Alex Flint
1y
10
108
Beyond Astronomical Waste
Wei_Dai
4y
41
24
Pitfalls of the agent model
Alex Flint
1y
4
16
Power-seeking for successive choices
adamShimi
1y
9
14
A review of "Agents and Devices"
adamShimi
1y
0