What is Consciousness and Can Machines have it? Part 1
summary
A formal model called the Conscious Turing Machine treats short‑term memory as a single-stage broadcast and long‑term processors as competitors that submit five‑part chunks (processor address, time, Brainish gist, valence weight and auxiliary intensity) into a perfect binary up‑tree tournament; coin‑flip nodes pick winners with probability proportional to importance, eliminating any central executive, then broadcast the winning chunk to all processors. A multimodal Brainish language and sleeping‑experts learning co‑evolve with a distributed Model‑of‑the‑World, yielding testable accounts of Libet timing, blindsight, change blindness and subjective feeling, and claiming buildable AGI‑relevant architecture.
AI-written summary · about
chapters (12)
- 0:00Introduction
- 2:43Lenore Blum's intro
- 5:14Conscious Turing Machine
- 8:04Easy vs hard problems
- 9:28Global workspace theory
- 13:21Formal CTM definition
- 17:01Up-tree competition
- 25:36Conscious attention
- 30:59Why CTM feels conscious
- 34:11Brainish and world model
- 43:19CTM vs theories
- 47:16Conclusion
related talks
01h 14mAI Consciousness is Inevitable: A Theoretical Computer Science Perspective
45mThe Conscious Turing Machine (CTM), a formally defined Theoretical model of Consciousness
59mCal Day Lecture: Can a Machine be Conscious? Towards a Conscious AI
43mThe Role of TCS in Understanding (AI) Consciousness
21mSentient AI – Can We Create Artificial Consciousness?
53mConsciousness and Large Language Models
38mA rocky road to general AI
01h 01mTowards “Thinking Machines”