Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
24 posts
Language Models
Robotics
5 posts
Definitions
Prompt Engineering
PaLM
163
Language models seem to be much better than humans at next-token prediction
Buck
4mo
56
157
Transformer Circuits
evhub
12mo
4
99
Help ARC evaluate capabilities of current language models (still need people)
Beth Barnes
5mo
6
84
Who models the models that model models? An exploration of GPT-3's in-context model fitting ability
Lovre
6mo
14
75
Inverse Scaling Prize: Round 1 Winners
Ethan Perez
2mo
16
64
RL with KL penalties is better seen as Bayesian inference
Tomek Korbak
6mo
15
61
Language Model Alignment Research Internships
Ethan Perez
1y
1
45
Deep learning curriculum for large language model alignment
Jacob_Hilton
5mo
3
42
NLP Position Paper: When Combatting Hype, Proceed with Caution
Sam Bowman
1y
15
42
Gears-Level Mental Models of Transformer Interpretability
KevinRoWang
8mo
4
40
Paper: Large Language Models Can Self-improve [Linkpost]
Evan R. Murphy
2mo
14
29
Hard-Coding Neural Computation
MadHatter
1y
8
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
113
The case for becoming a black-box investigator of language models
Buck
7mo
19
106
Testing PaLM prompts on GPT3
Yitz
8mo
15
44
Compact vs. Wide Models
Vaniver
4y
5
37
The Problem With The Current State of AGI Definitions
Yitz
6mo
22
7
Disentangling inner alignment failures
Erik Jenner
2mo
5