Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
AI Persuasion
Tag
Last edit:
26 Apr 2022 13:49 UTC
by
plex
AI which is highly capable of persuading people might have significant effects on humanity.
Relevant
New
Old
Persuasion Tools: AI takeover without AGI or agency?
Daniel Kokotajlo
20 Nov 2020 16:54 UTC
85
points
25
comments
11
min read
LW
link
1
review
Risks from AI persuasion
Beth Barnes
24 Dec 2021 1:48 UTC
76
points
15
comments
31
min read
LW
link
How it feels to have your mind hacked by an AI
blaked
12 Jan 2023 0:33 UTC
358
points
220
comments
17
min read
LW
link
On The Current Status Of AI Dating
Nikita Brancatisano
7 Feb 2023 20:00 UTC
52
points
8
comments
6
min read
LW
link
What 2026 looks like
Daniel Kokotajlo
6 Aug 2021 16:14 UTC
487
points
154
comments
16
min read
LW
link
1
review
I played the AI Box Experiment again! (and lost both games)
Tuxedage
27 Sep 2013 2:32 UTC
62
points
123
comments
11
min read
LW
link
One True Love
Zvi
9 Feb 2024 15:10 UTC
33
points
7
comments
10
min read
LW
link
(thezvi.wordpress.com)
AGI isn’t just a technology
Seth Herd
1 Sep 2023 14:35 UTC
18
points
12
comments
2
min read
LW
link
[Question]
Bayesian Persuasion?
Karthik Tadepalli
28 May 2022 17:52 UTC
8
points
2
comments
1
min read
LW
link
I attempted the AI Box Experiment (and lost)
Tuxedage
21 Jan 2013 2:59 UTC
79
points
245
comments
5
min read
LW
link
How To Win The AI Box Experiment (Sometimes)
pinkgothic
12 Sep 2015 12:34 UTC
55
points
21
comments
22
min read
LW
link
I Am Scared of Posting Negative Takes About Bing’s AI
Yitz
17 Feb 2023 20:50 UTC
63
points
28
comments
1
min read
LW
link
Can We Predict Persuasiveness Better Than Anthropic?
Lennart Finke
4 Aug 2024 14:05 UTC
22
points
5
comments
4
min read
LW
link
The reward function is already how well you manipulate humans
Kerry
19 Oct 2022 1:52 UTC
20
points
9
comments
2
min read
LW
link
Did ChatGPT just gaslight me?
TW123
1 Dec 2022 5:41 UTC
123
points
45
comments
9
min read
LW
link
(aiwatchtower.substack.com)
[Question]
Oracle AGI—How can it escape, other than security issues? (Steganography?)
RationalSieve
25 Dec 2022 20:14 UTC
3
points
6
comments
1
min read
LW
link
AI scares and changing public beliefs
Seth Herd
6 Apr 2023 18:51 UTC
45
points
21
comments
6
min read
LW
link
Let’s use AI to harden human defenses against AI manipulation
Tom Davidson
17 May 2023 23:33 UTC
34
points
7
comments
24
min read
LW
link
A simple presentation of AI risk arguments
Seth Herd
26 Apr 2023 2:19 UTC
16
points
0
comments
2
min read
LW
link