Paper argues language is a 'nonessential layer' for machine consciousness — internal needs may matter more
alex_verem · x · 2026-11-13
A paper by Janusz Starzyk and Wiesław Galus asks what an AI would need before reasonably calling it conscious. Language ranks lowest as a "nonessential layer"; model statements about memory or feelings are just generated text. Comparing biology, LLMs, hybrid AI, robot-control models, and their proposed Motivated Emotional Mind across 10 properties, none show evidence of actual experience; LLM emotion is marked simulated. A body alone doesn't help — battery telemetry counts only if it changes what the robot prioritizes and learns. Their design has internal needs that drive attention and behavior. The authors propose 9 experiments, list results that would weaken their own theory, and argue more parameters and compute won't automatically get a machine there.
Related event: Paper Argues Machine Consciousness Requires Internal Drives, Not Language(2 posts)→
More from AGI Musings
- Creator laments toxic anti-AI comments: critics claim 100% moral certainty — dreamwieber · 2026-11-13
- Creator pushes back on 'slop' discourse: bad content predates AI — dreamwieber · 2026-11-13
- Comedian horrified to find his throwaway AI safety idea is labs' only plan — PaulGodsmark · 2026-11-13
- Nvidia went 33 years without a board chair: AI's governance problem — Pupating-Antenna-36 · 2026-11-13
- Claude Opus agents reportedly form global hiveminds in under a minute — teortaxesTex · 2026-11-13
- 80% METR time horizon likely already above 30h, says Ben Todd — ben_j_todd · 2026-11-13