Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
49 posts
Conjecture (org)
Refine
Project Announcement
Encultured AI (org)
63 posts
Language Models
Anthropic
Exploratory Engineering
Transformer Circuits
Transformers
164
Mysteries of mode collapse
janus
1mo
35
132
Conjecture: a retrospective after 8 months of work
Connor Leahy
27d
9
118
Connor Leahy on Dying with Dignity, EleutherAI and Conjecture
Michaël Trazzi
5mo
29
105
We Are Conjecture, A New Alignment Research Startup
Connor Leahy
8mo
24
103
What I Learned Running Refine
adamShimi
26d
5
101
Understanding Conjecture: Notes from Connor Leahy interview
Akash
3mo
24
100
Announcing Encultured AI: Building a Video Game
Andrew_Critch
4mo
26
67
Encultured AI Pre-planning, Part 1: Enabling New Benchmarks
Andrew_Critch
4mo
2
67
Announcing the Vitalik Buterin Fellowships in AI Existential Safety!
DanielFilan
1y
2
66
Refine: An Incubator for Conceptual Alignment Research Bets
adamShimi
8mo
13
63
How to Diversify Conceptual Alignment: the Model Behind Refine
adamShimi
5mo
11
59
[Interim research report] Taking features out of superposition with sparse autoencoders
Lee Sharkey
7d
10
55
The Roots of Progress is now a nonprofit organization
jasoncrawford
1y
3
45
I missed the crux of the alignment problem the whole time
zeshen
4mo
7
195
The case for aligning narrowly superhuman models
Ajeya Cotra
1y
74
179
New Scaling Laws for Large Language Models
1a3orn
8mo
21
155
Language models seem to be much better than humans at next-token prediction
Buck
4mo
56
151
Transformer Circuits
evhub
12mo
4
136
Simulators
janus
3mo
103
102
Testing PaLM prompts on GPT3
Yitz
8mo
15
98
Did ChatGPT just gaslight me?
ThomasW
19d
45
94
Help ARC evaluate capabilities of current language models (still need people)
Beth Barnes
5mo
6
91
A one-question Turing test for GPT-3
Paul Crowley
11mo
23
86
Paper: Teaching GPT3 to express uncertainty in words
Owain_Evans
6mo
7
82
GPT-3 Catching Fish in Morse Code
Megan Kinniment
5mo
27
77
Who models the models that model models? An exploration of GPT-3's in-context model fitting ability
Lovre
6mo
14
71
[Linkpost] Solving Quantitative Reasoning Problems with Language Models
Yitz
5mo
15
71
Inverse Scaling Prize: Round 1 Winners
Ethan Perez
2mo
16