RSS

Joe_Carlsmith

Karma: 3,428

Senior research analyst at Open Philanthropy. Doctorate in philosophy at the University of Oxford. Opinions my own.

Video and tran­script of pre­sen­ta­tion on Schem­ing AIs

Joe_CarlsmithMar 22, 2024, 3:56 PM
23 points
1 commentEA link

On green

Joe_CarlsmithMar 21, 2024, 5:38 PM
61 points
3 commentsEA link

On the abo­li­tion of man

Joe_CarlsmithJan 18, 2024, 6:17 PM
71 points
4 commentsEA link

Be­ing nicer than Clippy

Joe_CarlsmithJan 16, 2024, 7:44 PM
26 points
3 commentsEA link

An even deeper atheism

Joe_CarlsmithJan 11, 2024, 5:28 PM
26 points
2 commentsEA link

Does AI risk “other” the AIs?

Joe_CarlsmithJan 9, 2024, 5:51 PM
23 points
3 commentsEA link

When “yang” goes wrong

Joe_CarlsmithJan 8, 2024, 4:35 PM
57 points
1 commentEA link

Deep athe­ism and AI risk

Joe_CarlsmithJan 4, 2024, 6:58 PM
65 points
4 commentsEA link

Gentle­ness and the ar­tifi­cial Other

Joe_CarlsmithJan 2, 2024, 6:21 PM
90 points
2 commentsEA link

Oth­er­ness and con­trol in the age of AGI

Joe_CarlsmithJan 2, 2024, 6:15 PM
37 points
1 commentEA link

Em­piri­cal work that might shed light on schem­ing (Sec­tion 6 of “Schem­ing AIs”)

Joe_CarlsmithDec 11, 2023, 4:30 PM
7 points
1 commentEA link

Sum­ming up “Schem­ing AIs” (Sec­tion 5)

Joe_CarlsmithDec 9, 2023, 3:48 PM
9 points
1 commentEA link

Speed ar­gu­ments against schem­ing (Sec­tion 4.4-4.7 of “Schem­ing AIs”)

Joe_CarlsmithDec 8, 2023, 9:10 PM
6 points
0 commentsEA link

Sim­plic­ity ar­gu­ments for schem­ing (Sec­tion 4.3 of “Schem­ing AIs”)

Joe_CarlsmithDec 7, 2023, 3:05 PM
6 points
1 commentEA link

The count­ing ar­gu­ment for schem­ing (Sec­tions 4.1 and 4.2 of “Schem­ing AIs”)

Joe_CarlsmithDec 6, 2023, 7:28 PM
9 points
1 commentEA link

Ar­gu­ments for/​against schem­ing that fo­cus on the path SGD takes (Sec­tion 3 of “Schem­ing AIs”)

Joe_CarlsmithDec 5, 2023, 6:48 PM
7 points
1 commentEA link

Non-clas­sic sto­ries about schem­ing (Sec­tion 2.3.2 of “Schem­ing AIs”)

Joe_CarlsmithDec 4, 2023, 6:44 PM
12 points
1 commentEA link

Does schem­ing lead to ad­e­quate fu­ture em­pow­er­ment? (Sec­tion 2.3.1.2 of “Schem­ing AIs”)

Joe_CarlsmithDec 3, 2023, 6:32 PM
6 points
1 commentEA link

The goal-guard­ing hy­poth­e­sis (Sec­tion 2.3.1.1 of “Schem­ing AIs”)

Joe_CarlsmithDec 2, 2023, 3:20 PM
6 points
1 commentEA link

How use­ful for al­ign­ment-rele­vant work are AIs with short-term goals? (Sec­tion 2.2.4.3 of “Schem­ing AIs”)

Joe_CarlsmithDec 1, 2023, 2:51 PM
6 points
0 commentsEA link