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

89Ought: why it matters and ways to help

paulfchristiano

6y

7

45Factored Cognition

7y

6

145Supervise Process, not Outcomes

stuhlmueller, jungofthewon

3y

9

103Solving Math Problems by Relay

Ben Goldhaber, Owain_Evans

5y

26

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

5y

1

17Automating reasoning about the future at Ought

5y

0

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

5y

0

4The Stack Overflow of Factored Cognition

6y

4

104Rant on Problem Factorization for Alignment

3y

53

71Elicit: Language Models as Research Assistants

stuhlmueller, jungofthewon

3y

6

70Current AI Safety Roles for Software Engineers

7y

9

64Prize for Alignment Research Tasks

stuhlmueller, William_S

3y

38

43Forecasting Thread: Existential Risk

5y

39

35Ought will host a factored cognition “Lab Meeting”

jungofthewon, stuhlmueller

3y

1

34Beta test GPT-3 based research assistant

4y

2