x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
LLM Personas — LessWrong
LLM Personas
This page is a stub.
Subscribe
Discussion
Subscribe
Discussion
Posts tagged
LLM Personas
Most Relevant
10
197
Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment
Ω
Cam
,
Puria
,
Kyle O’Brien
,
David Africa
,
Samuel Ratnam
,
andyk
3mo
Ω
25
8
698
Simulators
Ω
janus
4y
Ω
169
8
408
the void
Ω
nostalgebraist
10mo
Ω
108
7
25
Experimental Evidence for Simulator Theory— Part 1: Emergent Misalignment and Weird Generalizations
RogerDearnaley
7d
0
7
21
Experimental Evidence for Simulator Theory— Part 2: The Scalers Strike Back
RogerDearnaley
7d
0
6
258
A Three-Layer Model of LLM Psychology
Ω
Jan_Kulveit
1y
Ω
17
6
174
Persona Parasitology
Raymond Douglas
1mo
37
6
106
Pretraining on Aligned AI Data Dramatically Reduces Misalignment—Even After Post-Training
Ω
RogerDearnaley
2mo
Ω
12
6
78
Shaping the exploration of the motivation-space matters for AI safety
Maxime Riché
,
Victor Gillioz
,
nielsrolf
,
Kajetan Dymkiewicz
,
Filip Sondej
,
RogerDearnaley
,
Daniel Tan
,
dillonkn
25d
13
5
745
The Rise of Parasitic AI
Adele Lopez
6mo
188
4
118
A Case for Model Persona Research
nielsrolf
,
Maxime Riché
,
Daniel Tan
3mo
11
4
67
The Bleeding Mind
Ω
Adele Lopez
3mo
Ω
11
4
40
Selection Pressures on LM Personas
Ω
Raymond Douglas
1y
Ω
0
3
64
Concrete research ideas on AI personas
nielsrolf
,
Maxime Riché
,
Daniel Tan
2mo
10
2
440
Claude 4.5 Opus' Soul Document
Richard Weiss
4mo
44