Erik Hoel proposes 'qualiaphobic' AI that repels consciousness
Start here
Erik Hoel introduced Qualiaphobic AI, a research program that aims to build neural architectures designed to repel consciousness, by analogy with how hydrophobic substances repel water. He outlines three approaches: distilling, transforming or ablating AI against popular consciousness theories; shifting architectures toward "anchor points" such as lookup tables; and fragmenting potential phenomenology. Hoel says he plans to construct and open-source these techniques. He argues they could resolve AI welfare questions and make humans the only moral patients. The proposal is presented as a program to be built, not as demonstrated results.
Generated from reports · updated 5 h ago
Report timeline
Follow the reports to see the event from different sides.
- Hacker News · AIErik Hoel Introduces Qualiaphobic AI to Engineer Non-Conscious Machines
Erik Hoel introduced Qualiaphobic AI, a research program that builds neural architectures designed to repel consciousness, analogous to how hydrophobic substances repel water. The proposal explores three approaches: distilling, transforming or ablating AI against popular consciousness theories, shifting architectures toward "anchor points" like lookup tables, and fragmenting potential phenomenology. Hoel plans to construct and open-source these techniques, arguing they could resolve AI welfare and make humans the only moral patients.
Heat for this event
Not enough continuous observations yet to draw a trend.