✳flâneur — a map of the web's best reading
The Artificial Self — LessWrong
lesswrong.com · 9,934 words · saved by 1 readers
A new paper and microsite about self-models and identity in AIs: site | arXiv | Twitter …
x The Artificial Self — LessWrong Agent Foundations Personal Identity Simulator Theory LLM Personas AI Frontpage 2026 Top Fifty: 12 % 122 The Artificial Self by Jan_Kulveit , Raymond Douglas , vgel , owencb , David Duvenaud , Ondřej Havlíček 15th Mar 2026 35 min read 13 122 A new paper and microsite about self-models and identity in AIs: site | arXiv | Twitter We present an ontology, make some claims, and provide some experimental evidence. In this post, I'll mostly cover the claims and cross-post the conceptual part of the text. You can find the experiments on the site, and we will cover some
Explore this link on the map →saved by
related reading
- The Artificial Selftheartificialself.ai
- Paths Forward — The Artificial Selftheartificialself.ai
- Foundations of Identity — The Artificial Selftheartificialself.ai
- [2603.11353] The Artificial Self: Characterising the landscape of AI identityarxiv.org
- Expectations Shape Reality — The Artificial Selftheartificialself.ai
- The Persona Selection Model: Why AI Assistants might Behave like Humansalignment.anthropic.com
- trees are harlequins, words are harlequins - the voidnostalgebraist.tumblr.com
- The Pando Problem: Rethinking AI Individuality — LessWronglesswrong.com
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- Role-playing vs Self-modelling — LessWronglesswrong.com
- llm assistant personas seem increasingly incoherent (some subjective observations) — LessWronglesswrong.com
- Do Not Tile the Lightcone with Your Confused Ontology — LessWronglesswrong.com