AI Persuasion

TagLast edit: 30 Dec 2024 10:08 UTC by Dakara

AI Persuasion is the ability of artificial intelligence systems to influence human beliefs, decisions, and behaviors.

Risks from AI persuasion

Beth Barnes24 Dec 2021 1:48 UTC

76 points

15 comments31 min readLW link

Persuasion Tools: AI takeover without AGI or agency?

Daniel Kokotajlo20 Nov 2020 16:54 UTC

85 points

25 comments11 min readLW link 1 review

How it feels to have your mind hacked by an AI

blaked12 Jan 2023 0:33 UTC

372 points

222 comments17 min readLW link

On The Current Status Of AI Dating

Nikita Brancatisano7 Feb 2023 20:00 UTC

53 points

8 comments6 min readLW link

What 2026 looks like

Daniel Kokotajlo6 Aug 2021 16:14 UTC

588 points

163 comments16 min readLW link 1 review

One True Love

Zvi9 Feb 2024 15:10 UTC

34 points

7 comments10 min readLW link

(thezvi.wordpress.com)

[Question] Bayesian Persuasion?

Karthik Tadepalli28 May 2022 17:52 UTC

8 points

2 comments1 min readLW link

I attempted the AI Box Experiment (and lost)

Tuxedage21 Jan 2013 2:59 UTC

79 points

246 comments5 min readLW link

I played the AI Box Experiment again! (and lost both games)

Tuxedage27 Sep 2013 2:32 UTC

62 points

123 comments11 min readLW link

How To Win The AI Box Experiment (Sometimes)

pinkgothic12 Sep 2015 12:34 UTC

56 points

21 comments22 min readLW link

AGI isn’t just a technology

Seth Herd1 Sep 2023 14:35 UTC

18 points

12 comments2 min readLW link

Take Precautionary Measures Against Superhuman AI Persuasion

Yitz12 Jul 2025 5:34 UTC

12 points

9 comments2 min readLW link

Anti-Superpersuasion Interventions

niplav and Claude+

23 Jul 2025 15:18 UTC

21 points

1 comment5 min readLW link

I Am Scared of Posting Negative Takes About Bing’s AI

Yitz17 Feb 2023 20:50 UTC

63 points

28 comments1 min readLW link

Methods of defense against AGI manipulation

MarkelKori28 Apr 2025 21:03 UTC

3 points

0 comments2 min readLW link

A simple presentation of AI risk arguments

Seth Herd26 Apr 2023 2:19 UTC

19 points

0 comments2 min readLW link

Can Persuasion Break AI Safety? Exploring the Interplay Between Fine-Tuning, Attacks, and Guardrails

Devina Jain4 Feb 2025 19:10 UTC

9 points

0 comments10 min readLW link

An Alternate History of the Future, 2025-2040

Mr Beastly24 Feb 2025 5:53 UTC

5 points

5 comments10 min readLW link

Did ChatGPT just gaslight me?

TW1231 Dec 2022 5:41 UTC

124 points

45 comments9 min readLW link

(aiwatchtower.substack.com)

AI scares and changing public beliefs

Seth Herd6 Apr 2023 18:51 UTC

48 points

23 comments6 min readLW link

The reward function is already how well you manipulate humans

Kerry19 Oct 2022 1:52 UTC

20 points

9 comments2 min readLW link

Let’s use AI to harden human defenses against AI manipulation

Tom Davidson17 May 2023 23:33 UTC

35 points

7 comments24 min readLW link

What is LMArena actually measuring?

Baybar16 Sep 2025 21:44 UTC

11 points

0 comments5 min readLW link

What Parasitic AI might tell us about LLMs Persuasion Capabilities

Baybar13 Sep 2025 20:39 UTC

11 points

5 comments4 min readLW link

[Question] Oracle AGI—How can it escape, other than security issues? (Steganography?)

RationalSieve25 Dec 2022 20:14 UTC

3 points

6 comments1 min readLW link

No comments.