The Artificial Self
AI systems are on track to take on important new roles. We explore how properties bundled for humans can be separated and remixed for machine-based minds.
Characterising the landscape of AI identity Raymond Douglas * , Jan Kulveit * , Ondřej Havlíček , Theia Pearson-Vogel , Owen Cotton-Barratt , David Duvenaud † Full version on arXiv Executive Summary AI systems are rapidly taking on roles that push us to view them as actors. But the concepts we reach for — intent, responsibility, self-interest, trust — are built for humans, and cannot easily be applied to entities that can be copied, simulated, and surgically edited. We cannot simply port across human interaction norms; they must be carefully translated. And in many cases, we have some choice i
Explore this link on the map →saved by
related reading
- The Artificial Self — LessWronglesswrong.com
- [2603.11353] The Artificial Self: Characterising the landscape of AI identityarxiv.org
- Paths Forward — The Artificial Selftheartificialself.ai
- Foundations of Identity — The Artificial Selftheartificialself.ai
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- Different senses in which two AIs can be “the same” — LessWronglesswrong.com
- The Persona Selection Model: Why AI Assistants might Behave like Humansalignment.anthropic.com
- Expectations Shape Reality — The Artificial Selftheartificialself.ai
- Aren’t developers regularly making their AIs nice and safe and obedient? | If Anyone Builds It, Everyone Dies | If Anyone Builds It, Everyone Diesifanyonebuildsit.com
- Current AIs seem pretty misaligned to me — LessWronglesswrong.com
- trees are harlequins, words are harlequins - the voidnostalgebraist.tumblr.com
- Role-playing vs Self-modelling — LessWronglesswrong.com