RSS

A.H.

Karma: 231

Op­ti­mized for Some­thing other than Win­ning or: How Cricket Re­sists Moloch and Good­hart’s Law

A.H.5 Jul 2023 12:33 UTC
53 points
25 comments4 min readLW link

Will 2024 be very hot? Should we be wor­ried?

A.H.29 Dec 2023 11:22 UTC
51 points
12 comments10 min readLW link

Nash Bar­gain­ing be­tween Subagents doesn’t solve the Shut­down Problem

A.H.25 Jan 2024 10:47 UTC
22 points
1 comment6 min readLW link

Is Con­struc­tor The­ory a use­ful tool for AI al­ign­ment?

A.H.29 Nov 2022 12:35 UTC
11 points
8 comments26 min readLW link

Align­ment as Func­tion Fitting

A.H.6 May 2023 11:38 UTC
7 points
0 comments12 min readLW link

A Land Tax For Britain

A.H.6 Jan 2024 15:52 UTC
6 points
9 comments4 min readLW link

A Ped­a­gog­i­cal Guide to Corrigibility

A.H.17 Jan 2024 11:45 UTC
6 points
3 comments16 min readLW link

UK Govern­ment pub­lishes “Fron­tier AI: ca­pa­bil­ities and risks” Dis­cus­sion Paper

A.H.26 Oct 2023 13:55 UTC
5 points
0 comments2 min readLW link
(www.gov.uk)

Should we max­i­mize the Geo­met­ric Ex­pec­ta­tion of Utility?

A.H.17 Apr 2024 10:37 UTC
5 points
17 comments9 min readLW link

[Question] A Ques­tion about Cor­rigi­bil­ity (2015)

A.H.27 Nov 2023 12:05 UTC
4 points
2 comments1 min readLW link