Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
128 posts
GPT
Bounties & Prizes (active)
QURI
AI Safety Public Materials
Squiggle
Generativity
112 posts
Conjecture (org)
Language Models
Refine
Project Announcement
Anthropic
Exploratory Engineering
Encultured AI (org)
Transformer Circuits
Transformers
314
Jailbreaking ChatGPT on Release Day
Zvi
18d
74
220
Humans Who Are Not Concentrating Are Not General Intelligences
sarahconstantin
3y
35
210
Hiring engineers and researchers to help align GPT-3
paulfchristiano
2y
14
202
Announcing the Inverse Scaling Prize ($250k Prize Pool)
Ethan Perez
5mo
14
180
interpreting GPT: the logit lens
nostalgebraist
2y
32
163
Developmental Stages of GPTs
orthonormal
2y
74
147
Announcing $5,000 bounty for (responsibly) ending malaria
lc
2mo
42
147
[$10k bounty] Read and compile Robin Hanson’s best posts
Richard_Ngo
1y
29
139
Can you get AGI from a Transformer?
Steven Byrnes
2y
39
134
[$20K in Prizes] AI Safety Arguments Competition
Dan H
7mo
543
126
AI Timelines via Cumulative Optimization Power: Less Long, More Short
jacob_cannell
2mo
32
122
Alignment As A Bottleneck To Usefulness Of GPT-3
johnswentworth
2y
57
112
Bad at Arithmetic, Promising at Math
cohenmacaulay
2d
17
104
Introducing Metaforecast: A Forecast Aggregator and Search Tool
NunoSempere
1y
6
808
Simulators
janus
3mo
103
267
We Are Conjecture, A New Alignment Research Startup
Connor Leahy
8mo
24
267
New Scaling Laws for Large Language Models
1a3orn
8mo
21
262
Mysteries of mode collapse
janus
1mo
35
234
Conjecture: a retrospective after 8 months of work
Connor Leahy
27d
9
234
Connor Leahy on Dying with Dignity, EleutherAI and Conjecture
Michaël Trazzi
5mo
29
180
Refine: An Incubator for Conceptual Alignment Research Bets
adamShimi
8mo
13
179
The case for aligning narrowly superhuman models
Ajeya Cotra
1y
74
173
Language models seem to be much better than humans at next-token prediction
Buck
4mo
56
148
Did ChatGPT just gaslight me?
ThomasW
19d
45
147
Who models the models that model models? An exploration of GPT-3's in-context model fitting ability
Lovre
6mo
14
138
GPT-3 Catching Fish in Morse Code
Megan Kinniment
5mo
27
133
Transformer Circuits
evhub
12mo
4
130
Current themes in mechanistic interpretability research
Lee Sharkey
1mo
3