LESSWRONG
Wikitags
LW

Ought

Written by Ben Pace last updated 22nd Jul 2020

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

Posts tagged Ought

10

89Ought: why it matters and ways to help

paulfchristiano

6y

7

9

45Factored Cognition

6y

6

2

145Supervise Process, not Outcomes

stuhlmueller, jungofthewon

3y

9

2

103Solving Math Problems by Relay

Ben Goldhaber, Owain_Evans

5y

26

2

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

5y

1

2

17Automating reasoning about the future at Ought

4y

0

2

15[AN #86]: Improving debate and factored cognition through human experiments

5y

0

2

4The Stack Overflow of Factored Cognition

6y

4

1

102Rant on Problem Factorization for Alignment

3y

53

1

71Elicit: Language Models as Research Assistants

stuhlmueller, jungofthewon

3y

6

1

70Current AI Safety Roles for Software Engineers

6y

9

1

64Prize for Alignment Research Tasks

stuhlmueller, William_S

3y

38

1

43Forecasting Thread: Existential Risk

5y

39

1

35Ought will host a factored cognition “Lab Meeting”

jungofthewon, stuhlmueller

3y

1

1

34Beta test GPT-3 based research assistant

4y

2