Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
55 posts
Language Models
Agency
Deconfusion
Scaling Laws
Tool AI
Definitions
Simulation Hypothesis
PaLM
Prompt Engineering
Philosophy of Language
Carving / Clustering Reality
Astronomical Waste
33 posts
Conjecture (org)
Refine
Project Announcement
Encultured AI (org)
Analogy
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
472
Simulators
janus
3mo
103
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
59
LOVE in a simbox is all you need
jacob_cannell
2mo
69
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
80
[Interim research report] Taking features out of superposition with sparse autoencoders
Lee Sharkey
7d
10
159
The Singular Value Decompositions of Transformer Weight Matrices are Highly Interpretable
beren
22d
27
183
Conjecture: a retrospective after 8 months of work
Connor Leahy
27d
9
213
Mysteries of mode collapse
janus
1mo
35
103
What I Learned Running Refine
adamShimi
26d
5
85
Conjecture Second Hiring Round
Connor Leahy
27d
0
64
Searching for Search
NicholasKees
22d
6
82
Current themes in mechanistic interpretability research
Lee Sharkey
1mo
3
123
Interpreting Neural Networks through the Polytope Lens
Sid Black
2mo
26
103
Announcing Encultured AI: Building a Video Game
Andrew_Critch
4mo
26
186
We Are Conjecture, A New Alignment Research Startup
Connor Leahy
8mo
24
49
My Thoughts on the ML Safety Course
zeshen
2mo
3
94
Circumventing interpretability: How to defeat mind-readers
Lee Sharkey
5mo
8
24
Embedding safety in ML development
zeshen
1mo
1