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
27
Discovering Language Model Behaviors with Model-Written Evaluations
evhub
4h
3
29
Take 11: "Aligning language models" should be weirder.
Charlie Steiner
2d
0
364
chinchilla's wild implications
nostalgebraist
4mo
114
164
Language models seem to be much better than humans at next-token prediction
Buck
4mo
56
88
Inverse Scaling Prize: Round 1 Winners
Ethan Perez
2mo
16
166
Announcing the Inverse Scaling Prize ($250k Prize Pool)
Ethan Perez
5mo
14
27
Inverse scaling can become U-shaped
Edouard Harris
1mo
15
52
Paper: Large Language Models Can Self-improve [Linkpost]
Evan R. Murphy
2mo
14
47
Smoke without fire is scary
Adam Jermyn
2mo
22
94
Help ARC evaluate capabilities of current language models (still need people)
Beth Barnes
5mo
6
15
Updates on scaling laws for foundation models from ' Transcending Scaling Laws with 0.1% Extra Compute'
Nick_Greig
1mo
2
112
Who models the models that model models? An exploration of GPT-3's in-context model fitting ability
Lovre
6mo
14
118
The case for becoming a black-box investigator of language models
Buck
7mo
19
83
Causal confusion as an argument against the scaling hypothesis
RobertKirk
6mo
30
472
Simulators
janus
3mo
103
59
LOVE in a simbox is all you need
jacob_cannell
2mo
69
57
Vingean Agency
abramdemski
3mo
13
56
Discovering Agents
zac_kenton
4mo
8
35
Why agents are powerful
Daniel Kokotajlo
6mo
7
25
[Intro to brain-like-AGI safety] 11. Safety ≠ alignment (but they’re close!)
Steven Byrnes
8mo
1
23
Some reasons why a predictor wants to be a consequentialist
Lauro Langosco
8mo
16
57
Looking Deeper at Deconfusion
adamShimi
1y
13
25
Agency: What it is and why it matters
Daniel Kokotajlo
1y
2
119
Beyond Astronomical Waste
Wei_Dai
4y
41
28
Beware over-use of the agent model
Alex Flint
1y
10
19
Pitfalls of the agent model
Alex Flint
1y
4
11
Power-seeking for successive choices
adamShimi
1y
9
10
A review of "Agents and Devices"
adamShimi
1y
0