Can transformers test AI consciousness? Functional equivalence keeps the person silent
tallmetommy · x · 2026-11-12
kevinnbass proposes that the AI consciousness hypothesis can be tested empirically by augmenting or replacing parts of a living human brain with transformers, citing Chalmers' conceptual groundwork.
tallmetommy points out the catch: if the transformer part is functionally equivalent, the person says "still me, still feel it" whether or not experience actually faded. The test only speaks if behavior breaks — equivalence itself keeps it silent. A substantive debate on the testability of machine consciousness.
More from AGI Musings
- After Adobe MAX, a design educator lists 10 fundamentals AI tools can't replace — rufusd · 2026-11-12
- Economist: AI is a super-powered shirking technology, effort collapses when unobservable — _akpiper · 2026-11-12
- Why AI transformation stalls on the left side of the quality-velocity U-curve — hazelcough · 2026-11-12
- RL pioneer John Langford joins Core Automation, a lab built around agent-driven research — JohnCLangford · 2026-11-12
- Humans have an additive mind, AIs a subtractive one: RL carves a Claude-shaped personality — _Stocko_ · 2026-11-12
- Mathematician Daniel Spielman on the AI-driven "Big Reset" in mathematics — stevenstrogatz · 2026-11-12