Skip to content

Jason Liang

1 paper in the library

Papers

Sort Most recent Most cited

Self-Transcendence: Achieving AGI via Chaotic Dynamics and Thermodynamic Attractors

Jason Liang

This position paper addresses the "Architectural Trap", a fundamental constraint in deep learning where systems effectively optimize parameters within a fixed architecture but cannot discover radically superior structural designs. This trap constitutes a barrier within a non-continuous, high-dimensional search space that gradient-based and conventional search methods are ill-equipped to cross....