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
213
Mysteries of mode collapse
janus
1mo
35
186
We Are Conjecture, A New Alignment Research Startup
Connor Leahy
8mo
24
183
Conjecture: a retrospective after 8 months of work
Connor Leahy
27d
9
176
Connor Leahy on Dying with Dignity, EleutherAI and Conjecture
Michaël Trazzi
5mo
29
123
Refine: An Incubator for Conceptual Alignment Research Bets
adamShimi
8mo
13
103
What I Learned Running Refine
adamShimi
26d
5
103
Announcing Encultured AI: Building a Video Game
Andrew_Critch
4mo
26
103
Understanding Conjecture: Notes from Connor Leahy interview
Akash
3mo
24
85
Conjecture Second Hiring Round
Connor Leahy
27d
0
82
Current themes in mechanistic interpretability research
Lee Sharkey
1mo
3
80
[Interim research report] Taking features out of superposition with sparse autoencoders
Lee Sharkey
7d
10
78
How to Diversify Conceptual Alignment: the Model Behind Refine
adamShimi
5mo
11
64
Searching for Search
NicholasKees
22d
6
64
Announcing the Vitalik Buterin Fellowships in AI Existential Safety!
DanielFilan
1y
2
472
Simulators
janus
3mo
103
223
New Scaling Laws for Large Language Models
1a3orn
8mo
21
187
The case for aligning narrowly superhuman models
Ajeya Cotra
1y
74
164
Language models seem to be much better than humans at next-token prediction
Buck
4mo
56
142
Transformer Circuits
evhub
12mo
4
123
Did ChatGPT just gaslight me?
ThomasW
19d
45
112
Who models the models that model models? An exploration of GPT-3's in-context model fitting ability
Lovre
6mo
14
110
GPT-3 Catching Fish in Morse Code
Megan Kinniment
5mo
27
103
Testing PaLM prompts on GPT3
Yitz
8mo
15
96
Paper: Teaching GPT3 to express uncertainty in words
Owain_Evans
6mo
7
94
Help ARC evaluate capabilities of current language models (still need people)
Beth Barnes
5mo
6
90
RL with KL penalties is better seen as Bayesian inference
Tomek Korbak
6mo
15
88
Inverse Scaling Prize: Round 1 Winners
Ethan Perez
2mo
16
84
A one-question Turing test for GPT-3
Paul Crowley
11mo
23