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.

Posts tagged Ought

10

89Ought: why it matters and ways to help

Ω

paulfchristiano

6y

Ω

7

9

7y

6

2

145Supervise Process, not Outcomes

Ω

stuhlmueller, jungofthewon

4y

Ω

9

2

103Solving Math Problems by Relay

Ben Goldhaber, Owain_Evans

5y

26

2

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

Ω

Owain_Evans

6y

Ω

1

2

17Automating reasoning about the future at Ought

jungofthewon

5y

0

2

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

Ω

Rohin Shah

6y

Ω

0

2

4The Stack Overflow of Factored Cognition

rmoehn

7y

4

1

110Rant on Problem Factorization for Alignment

Ω

johnswentworth

3y

Ω

53

1

73Elicit: Language Models as Research Assistants

Ω

stuhlmueller, jungofthewon

4y

Ω

6

1

70Current AI Safety Roles for Software Engineers

ozziegooen

7y

9

1

64Prize for Alignment Research Tasks

Ω

stuhlmueller, William_S

4y

Ω

38

1

43Forecasting Thread: Existential Risk

Q

Amandango

5y

Q

39

1

35Ought will host a factored cognition “Lab Meeting”

Ω

jungofthewon, stuhlmueller

3y

Ω

1

34Beta test GPT-3 based research assistant

jungofthewon

5y

2

LESSWRONG
LW

LESSWRONG
LW

Ought