> -----Original Message----- > From: Matt Mahoney via AGI [mailto:[email protected]] > Subject: Re: [agi] Consciousness 101 > > On Wed, Jan 14, 2015 at 5:52 PM, Colin Geoffrey Hales via AGI > <[email protected]> wrote: > > https://www.youtube.com/watch?v=6i9kE3Ne7as > > > 1. "What it's like", distinct from the mental state of being awake. > 2. Ability to respond to sensory input in a way that you would expect a human > to react, independent of brain defects or injury such as the lack of a > hippocampus (long term memory), emotions, language (aphasia), ability to > move (locked in syndrome), etc. > 3. Tononi's integrated information (phi), which Koch interprets as the maximum > increase in complexity (in bits) of the system over all possible partitions. > (The > interpretation is important because Tononi does not rigorously define phi. > Maguire et. al. show that under a reasonable information-theoretic > interpretation that phi is not computable. http://arxiv.org/abs/1405.0126 ). > 4. Ability to pass a "what is wrong with this picture" test, in which pictures > depict common objects that don't belong together (for example, a man > standing sideways in mid air). >
This is what's needed and I'll throw it out there again impromptu. We need some measure of consciousness for agents, we acknowledge some parts of it are difficult to measure accurately. Consciousness is multi-component. Humans compared to each other have similar consciousness signatures but still have differences between them. Intelligent agents, even the fridge nowadays connect to the internet and have some "conscious" awareness. Let's say a 3D view signature. Each component is a vector emanating from the center. The test has minimalistic HTTP interface, JSON with support for images and media, and the test is along the lines of the acid tests (not the 60's acid test) e.g. Acid 3 http://www.acidtests.org/. Those acid tests are simple and limited but we are not so we can do better. Then, IoT devices, (Internet of Things) conform to the HTTP interface, connect, and are tested producing a sig stored in a public database. People can take the test as well. The 3D sig's vectors are measured along the lines of awareness, complexity perception, etc... There might be a better sig than the 3D but a momentary snapshot image of consciousness can be communicated instantly via this method. We could also do a 2D wheel for easy comparison and indexing maybe that's better not sure. An issue with this though is that some devices might benefit from hiding consciousness. I don't want devices spying on me so we might need an intrusive test like this for both intelligence and consciousness. or that might be a separate issue. So - how does all this apply to AGI? All these conscious entities networked together produce a consciousness flow that aligns on a globally distributed emerging self-organizing intelligence graph. John ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
