62 lines
1.8 KiB
Markdown
62 lines
1.8 KiB
Markdown
|
---
|
||
|
|
date: '2022-12-19T14:20:33'
|
||
|
|
hypothesis-meta:
|
||
|
|
created: '2022-12-19T14:20:33.068063+00:00'
|
||
|
|
document:
|
||
|
|
title:
|
||
|
|
- My AI Safety Lecture for UT Effective Altruism
|
||
|
|
flagged: false
|
||
|
|
group: __world__
|
||
|
|
hidden: false
|
||
|
|
id: TGVxKn-oEe2vUGtB_ufnbw
|
||
|
|
links:
|
||
|
|
html: https://hypothes.is/a/TGVxKn-oEe2vUGtB_ufnbw
|
||
|
|
incontext: https://hyp.is/TGVxKn-oEe2vUGtB_ufnbw/scottaaronson.blog/?p=6823
|
||
|
|
json: https://hypothes.is/api/annotations/TGVxKn-oEe2vUGtB_ufnbw
|
||
|
|
permissions:
|
||
|
|
admin:
|
||
|
|
- acct:ravenscroftj@hypothes.is
|
||
|
|
delete:
|
||
|
|
- acct:ravenscroftj@hypothes.is
|
||
|
|
read:
|
||
|
|
- group:__world__
|
||
|
|
update:
|
||
|
|
- acct:ravenscroftj@hypothes.is
|
||
|
|
tags:
|
||
|
|
- ai
|
||
|
|
- nlproc
|
||
|
|
target:
|
||
|
|
- selector:
|
||
|
|
- endContainer: /div[2]/div[2]/div[2]/div[1]/p[49]
|
||
|
|
endOffset: 48
|
||
|
|
startContainer: /div[2]/div[2]/div[2]/div[1]/p[49]
|
||
|
|
startOffset: 33
|
||
|
|
type: RangeSelector
|
||
|
|
- end: 19549
|
||
|
|
start: 19534
|
||
|
|
type: TextPositionSelector
|
||
|
|
- exact: " \u201CAI alignment\u201D"
|
||
|
|
prefix: t the other end of the spectrum,
|
||
|
|
suffix: ' is where you believe that reall'
|
||
|
|
type: TextQuoteSelector
|
||
|
|
source: https://scottaaronson.blog/?p=6823
|
||
|
|
text: AI Alignment is terminator situation. This versus AI Ethics which is more
|
||
|
|
the concern around current models being racist etc.
|
||
|
|
updated: '2022-12-19T14:20:33.068063+00:00'
|
||
|
|
uri: https://scottaaronson.blog/?p=6823
|
||
|
|
user: acct:ravenscroftj@hypothes.is
|
||
|
|
user_info:
|
||
|
|
display_name: James Ravenscroft
|
||
|
|
in-reply-to: https://scottaaronson.blog/?p=6823
|
||
|
|
tags:
|
||
|
|
- ai
|
||
|
|
- nlproc
|
||
|
|
- hypothesis
|
||
|
|
type: annotation
|
||
|
|
url: /annotations/2022/12/19/1671459633
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
<blockquote> “AI alignment”</blockquote>AI Alignment is terminator situation. This versus AI Ethics which is more the concern around current models being racist etc.
|