This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Wikitags
Ought
Edited by
Ben Pace
last updated
22nd Jul 2020
Ought
is an AI alignment research non-profit focused on the problem of
Factored Cognition
.
Subscribe
Subscribe
Discussion
0
Discussion
0
Posts tagged
Ought
Most Relevant
89
Ought: why it matters and ways to help
Ω
paulfchristiano
6y
Ω
7
45
Factored Cognition
Ω
stuhlmueller
7y
Ω
6
145
Supervise Process, not Outcomes
Ω
stuhlmueller
,
jungofthewon
3y
Ω
9
103
Solving Math Problems by Relay
Ben Goldhaber
,
Owain_Evans
5y
26
29
Update on Ought's experiments on factored evaluation of arguments
Ω
Owain_Evans
6y
Ω
1
17
Automating reasoning about the future at Ought
jungofthewon
5y
0
15
[AN #86]: Improving debate and factored cognition through human experiments
Ω
Rohin Shah
6y
Ω
0
4
The Stack Overflow of Factored Cognition
rmoehn
6y
4
106
Rant on Problem Factorization for Alignment
Ω
johnswentworth
3y
Ω
53
71
Elicit: Language Models as Research Assistants
Ω
stuhlmueller
,
jungofthewon
3y
Ω
6
70
Current AI Safety Roles for Software Engineers
ozziegooen
7y
9
64
Prize for Alignment Research Tasks
Ω
stuhlmueller
,
William_S
3y
Ω
38
43
Forecasting Thread: Existential Risk
Q
Amandango
5y
Q
39
35
Ought will host a factored cognition “Lab Meeting”
Ω
jungofthewon
,
stuhlmueller
3y
Ω
1
34
Beta test GPT-3 based research assistant
jungofthewon
5y
2