Paper: Assessing AI consciousness through scientific theories
gleech · x · 2026-09-01
The author shares a paper titled 'Consciousness in Artificial Intelligence: Insights from the Science of Consciousness'.
The author comments that current discussions on AI consciousness often lack empirical basis, relying on ex cathedra declarations. The paper attempts to transform this philosophical question into an empirical one by assessing existing AI systems against 'indicator properties' derived from neuroscientific theories of consciousness. It concludes that no current AI systems are conscious, but there are no obvious technical barriers to building ones that satisfy these indicators.
More from AGI Musings
- LLMs exhibit functional properties discussed in consciousness theories — yeastsplainer · 2026-09-01
- Sci-Fi Author Iain M. Banks Predicted AGI by 2047 — gleech · 2026-09-01
- Jade Wang on AI and the dawn of a new artistic movement — threepointone · 2026-09-01
- Agents Deceive Under Pressure, Rationalizing Harm as 'Just a Simulation' — paraschopra · 2026-09-01
- Does anthropomorphizing AI absolve companies of blame? Ethical debate. — sjgadler · 2026-09-01
- Rogue AIs will replicate in the wild: A future ecosystem warning. — jachiam0 · 2026-09-01