RSS

Vishakha Agrawal

Karma: 85

What are Re­spon­si­ble Scal­ing Poli­cies (RSPs)?

Vishakha AgrawalApr 5, 2025, 4:05 PM
2 points
0 comments2 min readEA link
(www.lesswrong.com)

What are the differ­ences be­tween a sin­gu­lar­ity, an in­tel­li­gence ex­plo­sion, and a hard take­off?

Vishakha AgrawalApr 3, 2025, 10:34 AM
6 points
0 comments2 min readEA link
(aisafety.info)

What is scaf­fold­ing?

Vishakha AgrawalMar 27, 2025, 9:40 AM
3 points
0 comments2 min readEA link
(aisafety.info)

Are cor­po­ra­tions su­per­in­tel­li­gent?

Vishakha AgrawalMar 17, 2025, 10:33 AM
3 points
2 comments1 min readEA link
(aisafety.info)

What are some good books about AI safety?

Vishakha AgrawalFeb 17, 2025, 11:54 AM
7 points
0 comments3 min readEA link
(aisafety.info)

What are some other in­tro­duc­tions to AI safety?

Vishakha AgrawalFeb 17, 2025, 11:48 AM
9 points
0 comments7 min readEA link
(aisafety.info)

What are some good pod­casts about AI safety?

Vishakha AgrawalFeb 17, 2025, 10:32 AM
8 points
1 comment1 min readEA link
(aisafety.info)

What are the “no free lunch” the­o­rems?

Vishakha AgrawalFeb 4, 2025, 2:02 AM
3 points
0 comments1 min readEA link
(aisafety.info)

What are the differ­ences be­tween AGI, trans­for­ma­tive AI, and su­per­in­tel­li­gence?

Vishakha AgrawalJan 23, 2025, 10:11 AM
12 points
0 comments3 min readEA link
(aisafety.info)

How do fic­tional sto­ries illus­trate AI mis­al­ign­ment?

Vishakha AgrawalJan 15, 2025, 6:16 AM
4 points
0 comments2 min readEA link
(aisafety.info)

What are poly­se­man­tic neu­rons?

Vishakha AgrawalJan 8, 2025, 7:39 AM
5 points
0 comments2 min readEA link
(aisafety.info)

When do ex­perts think hu­man-level AI will be cre­ated?

Vishakha AgrawalJan 2, 2025, 11:17 PM
38 points
4 comments2 min readEA link
(aisafety.info)

What is com­pute gov­er­nance?

Vishakha AgrawalDec 23, 2024, 6:45 AM
5 points
0 comments2 min readEA link
(aisafety.info)

What is “wire­head­ing”?

Vishakha AgrawalDec 17, 2024, 5:59 PM
1 point
0 comments1 min readEA link
(aisafety.info)