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
26
Discovering Language Model Behaviors with Model-Written Evaluations
evhub
4h
3
31
Take 11: "Aligning language models" should be weirder.
Charlie Steiner
2d
0
494
chinchilla's wild implications
nostalgebraist
4mo
114
101
Inverse Scaling Prize: Round 1 Winners
Ethan Perez
2mo
16
165
Language models seem to be much better than humans at next-token prediction
Buck
4mo
56
191
Announcing the Inverse Scaling Prize ($250k Prize Pool)
Ethan Perez
5mo
14
25
Updates on scaling laws for foundation models from ' Transcending Scaling Laws with 0.1% Extra Compute'
Nick_Greig
1mo
2
64
Paper: Large Language Models Can Self-improve [Linkpost]
Evan R. Murphy
2mo
14
26
Inverse scaling can become U-shaped
Edouard Harris
1mo
15
49
Smoke without fire is scary
Adam Jermyn
2mo
22
140
Who models the models that model models? An exploration of GPT-3's in-context model fitting ability
Lovre
6mo
14
89
Help ARC evaluate capabilities of current language models (still need people)
Beth Barnes
5mo
6
101
Causal confusion as an argument against the scaling hypothesis
RobertKirk
6mo
30
116
RL with KL penalties is better seen as Bayesian inference
Tomek Korbak
6mo
15
759
Simulators
janus
3mo
103
62
LOVE in a simbox is all you need
jacob_cannell
2mo
69
79
Discovering Agents
zac_kenton
4mo
8
51
Vingean Agency
abramdemski
3mo
13
37
Why agents are powerful
Daniel Kokotajlo
6mo
7
66
Looking Deeper at Deconfusion
adamShimi
1y
13
23
[Intro to brain-like-AGI safety] 11. Safety ≠ alignment (but they’re close!)
Steven Byrnes
8mo
1
22
Some reasons why a predictor wants to be a consequentialist
Lauro Langosco
8mo
16
26
Agency: What it is and why it matters
Daniel Kokotajlo
1y
2
130
Beyond Astronomical Waste
Wei_Dai
4y
41
18
Beware over-use of the agent model
Alex Flint
1y
10
14
Pitfalls of the agent model
Alex Flint
1y
4
6
A review of "Agents and Devices"
adamShimi
1y
0
6
Power-seeking for successive choices
adamShimi
1y
9