RSS

Ought

TagLast edit: 22 Jul 2020 9:01 UTC by Ben Pace

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

Ought will host a fac­tored cog­ni­tion “Lab Meet­ing”

9 Sep 2022 23:46 UTC
35 points
1 comment1 min readLW link

Rant on Prob­lem Fac­tor­iza­tion for Alignment

johnswentworth5 Aug 2022 19:23 UTC
89 points
51 comments6 min readLW link

Prize for Align­ment Re­search Tasks

29 Apr 2022 8:57 UTC
64 points
38 comments10 min readLW link

Elicit: Lan­guage Models as Re­search Assistants

9 Apr 2022 14:56 UTC
71 points
6 comments13 min readLW link

Su­per­vise Pro­cess, not Outcomes

5 Apr 2022 22:18 UTC
134 points
9 comments10 min readLW link

GPT-3 and the fu­ture of knowl­edge work

fowlertm5 Mar 2021 17:40 UTC
16 points
0 comments2 min readLW link

Beta test GPT-3 based re­search assistant

jungofthewon16 Dec 2020 13:42 UTC
34 points
2 comments1 min readLW link

Au­tomat­ing rea­son­ing about the fu­ture at Ought

jungofthewon9 Nov 2020 21:51 UTC
17 points
0 comments1 min readLW link
(ought.org)

[Question] Fore­cast­ing Thread: Ex­is­ten­tial Risk

Amandango22 Sep 2020 3:44 UTC
43 points
39 comments2 min readLW link

Solv­ing Math Prob­lems by Relay

17 Jul 2020 15:32 UTC
103 points
26 comments7 min readLW link

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

Rohin Shah12 Feb 2020 18:10 UTC
15 points
0 comments9 min readLW link
(mailchi.mp)

Up­date on Ought’s ex­per­i­ments on fac­tored eval­u­a­tion of arguments

Owain_Evans12 Jan 2020 21:20 UTC
29 points
1 comment1 min readLW link
(ought.org)

Ought: why it mat­ters and ways to help

paulfchristiano25 Jul 2019 18:00 UTC
89 points
7 comments5 min readLW link

The Stack Overflow of Fac­tored Cognition

rmoehn21 Apr 2019 12:19 UTC
4 points
4 comments3 min readLW link

Fac­tored Cognition

stuhlmueller5 Dec 2018 1:01 UTC
45 points
6 comments17 min readLW link

Cur­rent AI Safety Roles for Soft­ware Engineers

ozziegooen9 Nov 2018 20:57 UTC
70 points
9 comments4 min readLW link
No comments.