Go Back
You can't go any further
Choose this branch
meritocratic
regular
democratic
hot
top
alive
90 posts
GPT
38 posts
Bounties & Prizes (active)
QURI
AI Safety Public Materials
Squiggle
Generativity
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
180
interpreting GPT: the logit lens
nostalgebraist
2y
32
163
Developmental Stages of GPTs
orthonormal
2y
74
139
Can you get AGI from a Transformer?
Steven Byrnes
2y
39
122
Alignment As A Bottleneck To Usefulness Of GPT-3
johnswentworth
2y
57
112
Bad at Arithmetic, Promising at Math
cohenmacaulay
2d
17
86
Collection of GPT-3 results
Kaj_Sotala
2y
24
85
What's the Least Impressive Thing GPT-4 Won't be Able to Do
Algon
4mo
80
83
New GPT3 Impressive Capabilities - InstructGPT3 [1/2]
simeon_c
9mo
10
76
To what extent is GPT-3 capable of reasoning?
TurnTrout
2y
74
71
Getting GPT-3 to predict Metaculus questions
MathiasKB
7mo
8
66
[ASoT] Finetuning, RL, and GPT's world prior
Jozdien
18d
8
202
Announcing the Inverse Scaling Prize ($250k Prize Pool)
Ethan Perez
5mo
14
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
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
104
Introducing Metaforecast: A Forecast Aggregator and Search Tool
NunoSempere
1y
6
99
How much chess engine progress is about adapting to bigger computers?
paulfchristiano
1y
23
93
Announcing AI Alignment Awards: $100k research contests about goal misgeneralization & corrigibility
Akash
28d
20
89
$20K In Bounties for AI Safety Public Materials
Dan H
4mo
7
79
NeurIPS ML Safety Workshop 2022
Dan H
4mo
2
71
Announcing the Forecasting Innovation Prize
ozziegooen
2y
5
66
Calling for Student Submissions: AI Safety Distillation Contest
Aris
8mo
15
66
£2000 bounty - contraceptives (and UTI) literature review
Chi Nguyen
1y
14
63
AI Risk Intro 1: Advanced AI Might Be Very Bad
TheMcDouglas
3mo
13