x

AI ALIGNMENT FORUM
AF

Ought — AI Alignment Forum

You are viewing version 1.0.0 of this page. Click here to view the latest version.

Ought

Edited by Ben Pace last updated 22nd Jul 2020

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

3

24Ought: why it matters and ways to help

paulfchristiano

6y

1

3

16Factored Cognition

7y

1

1

69Supervise Process, not Outcomes

stuhlmueller, jungofthewon

4y

2

1

10Update on Ought's experiments on factored evaluation of arguments

6y

1

1

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

6y

0

0

45Rant on Problem Factorization for Alignment

3y

32

1

26Elicit: Language Models as Research Assistants

stuhlmueller, jungofthewon

4y

4

1

29Prize for Alignment Research Tasks

stuhlmueller, William_S

4y

6

1

15Ought will host a factored cognition “Lab Meeting”

jungofthewon, stuhlmueller

3y

1

Add Posts