x

LESSWRONG
LW

LLM Personas — LessWrong

LLM Personas

This page is a stub.

Add Posts

Posts tagged LLM Personas

10

184Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment

Cam, Puria Radmard, Kyle O’Brien, David Africa, Samuel Ratnam, andyk

1mo

23

8

3y

169

6

8mo

107

6

102Pretraining on Aligned AI Data Dramatically Reduces Misalignment—Even After Post-Training

12d

12

4

250A Three-Layer Model of LLM Psychology

1y

17

3

716The Rise of Parasitic AI

4mo

179

2

440Claude 4.5 Opus' Soul Document

2mo

44

2

198How I stopped being sure LLMs are just making up their internal experience (but the topic is still confusing)

1mo

66

2

109A Case for Model Persona Research

nielsrolf, Maxime Riché, Daniel Tan

2mo

8

2

82How AI Manipulates—A Case Study

4mo

27

2

65The Bleeding Mind

1mo

10

2

51Should AI Developers Remove Discussion of AI Misalignment from AI Training Data?

3mo

3

2

40Selection Pressures on LM Personas

Raymond Douglas

10mo

0

2

38Silicon Morality Plays: The Hyperstition Progress Report

2mo

7

2

37Special Persona Training: Hyperstition Progress Report 2

1mo

2

Load More (15/20)

Add Posts