Hoel proposes Qualiaphobic AI architecture, arguing AI should be unconscious
Understand this story
Erik Hoel has proposed a research program called Qualiaphobic AI, arguing for building "consciousness-repelling" neural network architectures that let AI hold justified beliefs about its own lack of consciousness, thereby making humans the only moral subjects in matters of AI welfare and civilizational alignment. According to Hoel, the implementation approaches include distillation, modification or ablation against mainstream theories of consciousness, moving toward "anchor" architectures such as lookup tables, and fragmenting latent phenomenology. The program will open-source the relevant technology.
AI overview based on source reports · Updated 1 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIIntroducing: Qualiaphobic AI – By Erik Hoel
Erik Hoel introduces a proposal for "qualiaphobic" artificial neural architectures that repel consciousness, analogous to hostile architecture, using an information asymmetry so that certainty about AI non-consciousness does not require solving the Hard Problem. He describes three approaches: distilling, transforming or ablating AI in ways adversarial to popular theories of consciousness; shifting architectures toward anchor points like lookup tables with known minimal potential for consciousness; and fragmenting any potential phenomenology. He argues that widely implemented qualiaphobic AI would address AI welfare and make humans the only moral patients, and he plans to construct and open-source the techniques.
Activity for this story
- Current comparable activity
- 4
- Peak comparable activity
- 9Nov 13 17:00
- Change in the past 24 hours
- -49%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.