Aditya Arpitha Prasad

-

Bio

Alignment researcher and organiser working on AI safety field-building in India, leading the Groundless Alignment Residency 2025 for Autostructures fellows to continue the Live Theory agenda and run research retreats.

Links

Personal Website: https://adityaarpitha.substack.com/
LinkedIn: -
Twitter / X: -
LessWrong: -
EA Forum: -

Organizations

Live Theory

field-building and residency organiser

Projects

Groundless Alignment Residency 2025

creator

Management of Substrate-Sensitive AI Capabilities (MoSSAIC)

co-author

Grants

Aditya Arpitha Prasad → Act I: Exploring emergent behavior from multi-AI, multi-human interaction

to Act I: Exploring emergent behavior from multi-AI, multi-human interactionmanifund.org

funder$30

Aditya Arpitha Prasad → Cadenza Labs: AI Safety research group working on own interpretability agenda

to Cadenza Labs: AI Safety research group working on own interpretability agenda