LESSWRONGTags
LW

Ought

EditHistorySubscribe

Help improve this page (2 flags)

EditHistorySubscribe

Help improve this page (2 flags)

Contributors

You are viewing revision 1.0.0, last edited by Ben Pace

Ought is an AI alignment research non-profit focused on the problem of Factored Cognition.

Posts tagged Ought

Most Relevant

10

87Ought: why it matters and ways to helpΩ

paulfchristiano

4y

7

9

45Factored CognitionΩ

4y

6

2

120Supervise Process, not OutcomesΩ

stuhlmueller, jungofthewon

1y

8

2

103Solving Math Problems by Relay

bgold, Owain_Evans

3y

26

2

29Update on Ought's experiments on factored evaluation of argumentsΩ

3y

0

2

17Automating reasoning about the future at Ought

2y

0

2

14[AN #86]: Improving debate and factored cognition through human experimentsΩ

3y

0

2

4The Stack Overflow of Factored Cognition

4y

4

1

74Rant on Problem Factorization for AlignmentΩ

8mo

48

1

70Current AI Safety Roles for Software Engineers

4y

9

1

70Elicit: Language Models as Research AssistantsΩ

stuhlmueller, jungofthewon

1y

7

1

63Prize for Alignment Research TasksΩ

stuhlmueller, William_S

1y

36

1

43Forecasting Thread: Existential RiskQ

3y

40

1

42The Majority Is Always Wrong

Eliezer Yudkowsky

16y

54

1

35Ought will host a factored cognition “Lab Meeting”Ω

jungofthewon, stuhlmueller

7mo

1