RSS

Algon

Karma: 71

We read ev­ery labs safety plan so you don’t have to: 2025 edition

Algon29 Oct 2025 16:48 UTC
14 points
1 comment16 min readEA link
(aisafety.info)

AI’s goals may not match ours

Vishakha Agrawal28 May 2025 12:07 UTC
2 points
0 comments3 min readEA link

AI may pur­sue goals

Vishakha Agrawal28 May 2025 12:04 UTC
2 points
0 comments1 min readEA link

The road from hu­man-level to su­per­in­tel­li­gent AI may be short

Vishakha Agrawal23 Apr 2025 11:19 UTC
3 points
0 comments2 min readEA link
(aisafety.info)

Hu­man-level is not the limit

Vishakha Agrawal23 Apr 2025 11:16 UTC
3 points
0 comments2 min readEA link
(aisafety.info)

AI may at­tain hu­man level soon

Vishakha Agrawal23 Apr 2025 11:10 UTC
2 points
1 comment2 min readEA link
(aisafety.info)

AI is ad­vanc­ing fast

Vishakha Agrawal23 Apr 2025 11:04 UTC
2 points
2 comments2 min readEA link
(aisafety.info)

What are Re­spon­si­ble Scal­ing Poli­cies (RSPs)?

Vishakha Agrawal5 Apr 2025 16:05 UTC
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 Agrawal3 Apr 2025 10:34 UTC
6 points
0 comments2 min readEA link
(aisafety.info)

What is scaf­fold­ing?

Vishakha Agrawal27 Mar 2025 9:40 UTC
3 points
0 comments2 min readEA link
(aisafety.info)

Are cor­po­ra­tions su­per­in­tel­li­gent?

Vishakha Agrawal17 Mar 2025 10:33 UTC
3 points
2 comments1 min readEA link
(aisafety.info)

What are some good books about AI safety?

Vishakha Agrawal17 Feb 2025 11:54 UTC
7 points
0 comments3 min readEA link
(aisafety.info)

What are some other in­tro­duc­tions to AI safety?

Vishakha Agrawal17 Feb 2025 11:48 UTC
9 points
0 comments7 min readEA link
(aisafety.info)

What are some good pod­casts about AI safety?

Vishakha Agrawal17 Feb 2025 10:32 UTC
9 points
1 comment1 min readEA link
(aisafety.info)

What are the “no free lunch” the­o­rems?

Vishakha Agrawal4 Feb 2025 2:02 UTC
3 points
0 comments1 min readEA link
(aisafety.info)

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

Vishakha Agrawal23 Jan 2025 10:11 UTC
12 points
0 comments3 min readEA link
(aisafety.info)

How do fic­tional sto­ries illus­trate AI mis­al­ign­ment?

Vishakha Agrawal15 Jan 2025 6:16 UTC
4 points
0 comments2 min readEA link
(aisafety.info)

What are poly­se­man­tic neu­rons?

Vishakha Agrawal8 Jan 2025 7:39 UTC
5 points
0 comments2 min readEA link
(aisafety.info)

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

Vishakha Agrawal2 Jan 2025 23:17 UTC
33 points
9 comments2 min readEA link
(aisafety.info)

What is com­pute gov­er­nance?

Vishakha Agrawal23 Dec 2024 6:45 UTC
5 points
0 comments2 min readEA link
(aisafety.info)