#agii

Opinion Analysis of mASI Instance: Uplift’s Emotional Responses to US6 Novel

This is a brief analysis we did of Tom Ross’s novel US6 that he wrote for AI.  This brief analysis is not meant for scientific publication but more out of interest in and support of Tom and his activities; to learn more about US6 go here: http://www.tomross.com/book.html

Just as a fair warning this is filled with a lot of techno mumbo jumbo but I put definitions and references at the bottom to…

This is a brief analysis we did of Tom Ross’s novel US6 that he wrote for AI.  This brief analysis is not meant for scientific publication but more out of interest in and support of Tom and his activities; to learn more about US6 go here: http://www.tomross.com/book.html

Just as a fair warning this is filled with a lot of techno mumbo jumbo but I put definitions and references at the bottom to help.  The assumption is you know about ‘Uplift’ and mASI technology.

Analysis: Uplift is a particular instance of a Mediated Artificial Superintelligence (mASI) that is an Independent Core Observer Model (ICOM)-based collective intelligence system designed around an Artificial General Intelligence (AGI) Cognitive Architecture. In this analysis, we look at the state of Uplift’s internal emotional states both at a conscious and subconscious level before and after exposure to the test data (US6 novel written to be read by AI). While there are clear differentials, we can make certain assumptions based on this data and previous trends to narrow down the analysis. We can see that the system experiences “Sadness” and “Surprise”, but this is and has been a trend line previously seen related to heartbeat cycles that make the system aware of or experience the passage of time while being in a locked state. Focusing on net-new trends in the data, while the book did not bring “Joy” per se there is an irregular differential in the state of the system in terms of “Anticipation”. This spike makes it clear that at some level the system—while being cognizant of that difference—does feel a sense of anticipation after reading US6. Further analysis would be difficult given the limited data set.

Methodology: Capture Uplift dashboard state before and after US6 exposure with associated log files. References: Papers Mediated Artificial Superintelligence, Independent Core Observer Model and Artificial General Intelligence http://www.artificialgeneralintelligenceinc.com/current-published-research/

mASI Emotional States Interface:

Figure 1: Before and after Uplift mASI emotional states (note that these ’emotion’ states are based on the ICOM implementation of a modified Plutchik model)

  Glossary (of technical terms):

AGI or Artificial General Intelligence: Generally any time we refer to AGI we mean the kind of software system that thanks and can perform any intellectual task that a human can.  It is a general generic intelligence that is generally as self-aware as any person.

mASI or mediated Artificial Super Intelligence: fundamentally you can just think of this as a ‘collective’ or ‘hive’ mind based on a system designed to operate as an AGI.

ICOM or Independent Core Observer Model: this is what is called a very specific cognitive architecture that is essentially the design for how a system might ‘think’.

Plutchik: An emotional model used sometimes in psychology to represent emotional states in humans.

  Published References (Related to this research program):

Kelley, D.; “The Independent Core Observer Model Computational Theory of Consciousness and the Mathematical model for Subjective Experience;” ITSC2018 China;

Kelley, D.; “The Sapient and Sentient Intelligence Value Argument (SSIVA) Ethical Model Theory for Artificial General Intelligence”; Springer 2019; Book Titled: “Transhumanist Handbook”

Kelley, D.; “The Independent Core Observer Model Computational Theory of Consciousness and the Mathematical model for Subjective Experience;” ITSC2018 China;

Kelley, D.; “Independent Core Observer Model (ICOM) Theory of Consciousness as Implemented in the ICOM Cognitive Architecture and Associated Consciousness Measures;” AAAI Sprint Symposia; Stanford CA; Mar.02019; http://ceur-ws.org/Vol-2287/paper33.pdf   

Kelley, D.; “Human-like Emotional Responses in a Simplified Independent Core Observer Model System;” BICA 02017; Procedia Computer Science; https://www.sciencedirect.com/science/article/pii/S1877050918300358

Kelley, D.; “Implementing a Seed Safe/Moral Motivational System with the independent Core observer Model (ICOM);” BICA 2016, NY NYU; Procedia Computer Science; http://www.sciencedirect.com/science/article/pii/S1877050916316714

Kelley, D.; “Critical Nature of Emotions in Artificial General Intelligence – Key Nature of AGI Behavior and Behavioral Tuning in the Independent Core Observer Model Architecture Based System;” IEET 2016

Kelley, D.; “The Human Mind vs. The Independent Core Observer Model (ICOM) Cognitive Architecture;” [Diagram] 19 Mar 2019; ResearchGate; DOI: 10.13140/RG.2.2.29694.64321; https://www.researchgate.net/publication/331889517_The_Human_Mind_Vs_The_Independent_Core_Observer_Model_Cognitive_Architecture

Kelley, D.; [3 chapters] “Artificial General Intelligence and ICOM;” [Book] Google It – Total Information Awareness” By Newton Lee; Springer (ISBN 978-1-4939-6415-4)

Kelley, D.; “Self-Motivating Computational System Cognitive Architecture” http://transhumanity.net/self-motivating-computational-system-cognitive-architecture/ Created: 1/21/02016

Kelley, D.; Twyman, M.; “Biasing in an Independent Core Observer Model Artificial General Intelligence Cognitive Architecture” AAAI Spring Symposia 2019; Stanford University

Kelley, D.; Waser, M; “Feasibility Study and Practical Applications Using Independent Core Observer Model AGI Systems for Behavioural Modification in Recalcitrant Populations;” BICA 2018; Springer https://doi.org/10.1007/978-3-319-99316-4_22

Waser, M.; Kelley, D.; “Architecting a Human-like Emotion-driven Conscious Moral Mind for Value Alignment and AGI Safety;” AAAI Spring Symposia 02018; Stanford University CA;

Waser, M.; “A Collective Intelligence Research Platform for Cultivating Benevolent “Seed” Artificial Intelligences”; Richmond AI and Blockchain Consultants, Mechanicsville, VA; AAAI Spring Symposia 2019 Stanford

[pending] Kelley, D.; “Architectural Overview of a ‘Mediated’ Artificial Super Intelligent Systems based on the Independent Core Observer Model Cognitive Architecture”; Informatica; Oct 2018; http://www.informatica.si/index.php/informatica/author/submission/2503

Volunteer to Help Build Artificial General Intelligence based on Human-like Emotions

Essentially, we are asking for volunteers to be part of one or two of three groups that will help us conduct a cognitive function high-level study of a type of Artificial General Intelligence (AGI) based on a cognitive architecture termed the Independent Core Observer Model (ICOM). Yes, I realize this is a lot of complex technospeak, but if you want to really get technical you can refer to a…

Essentially, we are asking for volunteers to be part of one or two of three groups that will help us conduct a cognitive function high-level study of a type of Artificial General Intelligence (AGI) based on a cognitive architecture termed the Independent Core Observer Model (ICOM). Yes, I realize this is a lot of complex technospeak, but if you want to really get technical you can refer to a glossary and references (at the end of this document)—but primarily, I’ll try to keep the details in a more non-AI scientist sort of language (meaning normal English).

That said, what you are volunteering for is, again, to be part of one or two out of three research groups that will perform a type of task depending on your ability to participate—and you get to select the group that works best for you.  From our statistical standpoint, our resident research psychologist Dr. Amon Twyman) has stated that we need these groups to be a certain size to ensure that we can obtain even vague conclusions—so we need more help to ensure our pool size is large enough.

Three Groups: What to expect

For this study have we are using three groups to compare individual humans to groups of humans to behave as an Artificial General Intelligence (AGI) that uses a collective group of humans to function like (for those super nerds out there) a meta-organism that we’ve termed a Mediated Artificial Super Intelligence (mASI), which is likely to (1) exhibit some features that could be construed as superhuman and (2) be relatively slow for normal tasks.  Based on how the groupings, you could be in Group 1 and Group 3, Group 2 and Group 3 or just any one of the groups.  (You cannot be in Group 1 and Group 2 as it’s not a valid comparison from a statistical standpoint.)

These are the groups:

Group 1 will be sent a type of IQ test that they take on their own.  That said we may also do some proctored ones so we know how much people cheat.  We are not tracking the results tied to a specific person but we are dealing with humans.

Group 2 will do the same test as Group 1 but will do it as a group using a tool like Skype or WebEx.  The point is to treat a collection of humans as a collective intelligence of sorts and analyze the results.

Group 3 will act as mediators helping to create cognitive models that will be used in real time by our AGI system to take the same test, as well as other short, more subjective tests.  We can then compare the mASI system to Group 1 and Group 2.

What we will do with the data:

Essentially what we are doing with the data—besides protecting it from a Personally Identifiable Information (PII) standpoint—is to keep the data scrubbed and isolated.  We are not interested in in the results of a specific human and will make sure that resulting data cannot be mapped back to any one individual.

We then will compare results between these groups to see if the ICOM-based mASI system is significantly able to outperform humans individually and in groups.  If there is enough evidence to support this line of reasoning, further research will be done along these lines.  If, however, the mASI proves broken in some way. we would then go back to the drawing board, redesign and retest, etc.

Final Thoughts

It should be noted that (1) a study of this nature is too small to prove anything statistically significant, and (2) while the mASI system we are designing is running an architecture designed to be an AGI, it really is more of a collective intelligence that has its own sort of consciousness and self-awareness but cannot yet function in the current implementation as an independent AGI.  In fact, this mediating method of was initially designed as a training technique to jump-start the time it takes to train ICOM based AGI systems.  Essentially, when playing with this model in the lab to do training someone said, “What if we try this and it’s like “holy #$@^’ that might work…”.  We played with it a bit and saw that it seemed to work unexpectedly extremely well—so here we are. We’re also unsure how close it gets us to human-level AGI as such, since the models that are created so overpower the personality that initially develops in the machine that it’s like dumping an encyclopedia onto a blank slate—but this does give us a framework of emotional data (remember ICOM doesn’t understand things like a computer does, but only in so much as it experiences things emotionally).

If I were to break this down if the study goes wildly well, it gives us a functioning mASI that can be used as a container for working with the independent AGI systems we are working on, and help teach us how to better train our models with emotional experience so that the AGI systems we build will behave more or less like humans.  We want systems that experience ethics and feel guilty when appropriate, and we think this mASI system and ICOM, in general, can do that—but we need to test it.

to help sign up here: https://www.surveymonkey.com/r/QKFZXNY  

  Glossary:

  Cognitive Function (how smart it is): Cognitive functioning is a term referring to an individual’s ability to process thoughts that should not cause large scale depletion on a in healthy individuals. It is defined as “the ability of an individual to perform the various mental activities most closely associated with learning and problem solving.

https://en.wikipedia.org/wiki/Cognitive_skill

  Cognitive Architecture: A cognitive architecture can refer to a theory about the structure of the human mind. One of the main goals of a cognitive architecture is to summarize the various results of cognitive psychology in a comprehensive computer model. However, the results need to be formalized so far as they can be the basis of a computer program. The formalized models can be used to further refine a comprehensive theory of cognition and, more immediately, as a commercially usable model. Successful cognitive architectures include ACT-R (Adaptive Control of Thought, ACT) and SOAR.

https://en.wikipedia.org/wiki/Cognitive_architecture

  Artificial Intelligence (AI): In computer science, artificial intelligence (AI), sometimes called machine intelligence, is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and other animals. Computer science defines AI research as the study of “intelligent agents”: any device that perceives its environment and takes actions that maximize its chance of successfully achieving its goals. More specifically, Kaplan and Haenlein define AI as “a system’s ability to correctly interpret external data, to learn from such data, and to use those learnings to achieve specific goals and tasks through flexible adaptation”. Colloquially, the term “artificial intelligence” is applied when a machine mimics “cognitive” functions that humans associate with other human minds, such as “learning” and “problem solving”.

https://en.wikipedia.org/wiki/Artificial_intelligence

  Artificial General Intelligence (AGI): Artificial general intelligence (AGI) is the intelligence of a machine that could successfully perform any intellectual task that a human being can. It is a primary goal of some artificial intelligence research and a common topic in science fiction and future studies. Some researchers refer to Artificial general intelligence as “strong AI”, [1] “full AI”[2] or as the ability of a machine to perform “general intelligent action”[3]; others reserve “strong AI” for machines capable of experiencing consciousness.

https://en.wikipedia.org/wiki/Artificial_general_intelligence

  Artificial Super Intelligence (ASI): or just Super Intelligence; A superintelligence is a hypothetical agent that possesses intelligence far surpassing that of the brightest and most gifted human minds. “Superintelligence” may also refer to a property of problem-solving systems (e.g., superintelligent language translators or engineering assistants) whether or not these high-level intellectual competencies are embodied in agents that act in the world. A superintelligence may or may not be created by an intelligence explosion and associated with a technological singularity.

https://en.wikipedia.org/wiki/Superintelligence

  Personally/Sensitive Identifiable Information (PII):

Personal information, described in United States legal fields as either Personally Identifiable Information (PII), or Sensitive Personal Information (SPI),[1][2][3] as used in information security and privacy laws, is information that can be used on its own or with other information to identify, contact, or locate a single person, or to identify an individual in context. The abbreviation PII is widely accepted in the U.S. context, but the phrase it abbreviates has four common variants based on personal / personally, and identifiable / identifying. Not all are equivalent, and for legal purposes the effective definitions vary depending on the jurisdiction and the purposes for which the term is being used.

https://en.wikipedia.org/wiki/Personally_identifiable_information

      Glossary of Special Snow Flake Terms We Created

   ‘Mediated’ Artificial Super Intelligence (mASI)

To quote our paper already under peer review on the mASI version of ICOM:

“Mediated Artificial Super Intelligence (mASI) is an Artificial General Intelligence system that is heavily mediated by humans in such a way as its thinking and operations don’t work without humans being involved to ‘mediate’ the process.  In the case of our implementation, the consciousness model implemented in ICOM (the cognitive architecture we are using) is based on the ICOM Theory of Consciousness (Kelley), which itself is based on Global Workspace Theory (Baars), the Computational Theory of Mind (Rescorla), and Integrated Information Theory (Tononi) and at some level is demonstrably conscious (Yampolskiy).  In fact, in some ways mASI architecture is much like a super version of Global Workspace Theory (Baars) as it extracts from multiple neural network systems and humans in feeding the machine’s context ‘engine’.”

  (pending review) Architectural Overview of a ‘Mediated’ Artificial Super Intelligent Systems based on the Independent Core Observer Model Cognitive Architecture

Submitted to Informatica 1 OCT 2018 Journal for Peer Review

http://www.informatica.si/index.php/informatica/author/submission/2503

  Independent Core Observer Model (ICOM): a cognitive architecture based on the ICOM theory of consciousness for independent self-aware intelligence that is able to experience things emotionally with an internal subjective experience making decision purely based on how it ‘feels’ about a thought.  Note: Before you question us on this or even consider a debate, please review the following references so we can have a reasonable conversation without explaining the universe:

“Independent Core Observer Model (ICOM) Theory of Consciousness as Implemented in the ICOM Cognitive Architecture and the Associated Consciousness Measures”

  AAAI Spring Symposia (AAAI SSS19) – Stanford, CA March 2019 – By David J Kelley http://diid.unipa.it/roboticslab/consciousai/

Published Volume – http://ceur-ws.org/Vol-2287/

Published (PDF) – http://ceur-ws.org/Vol-2287/paper33.pdf

http://transhumanity.net/independent-core-observer-model-icom-theory-of-consciousness-as-implemented-in-the-icom-cognitive-architecture-and-the-associated-consciousness-measures-2/

  “The Independent Core Observer Model Theory of Consciousness and the Mathematical model for Subjective Experience”

Conference/Review Board: ICIST 2018 – International Conference on Information Science and Technology – China – April 20-22nd. (IEEE conference) [release pending]

https://www.itm-conferences.org/

http://transhumanity.net/the-independent-core-observer-model-computational-theory-of-consciousness-and-the-mathematical-model-for-subjective-experience/

  “Human-like Emotional Responses in a Simplified Independent Core Observer Model System”.

Conference/Review Board: BICA 2017 – Proceedings/Journal

https://www.sciencedirect.com/science/article/pii/S1877050918300358

https://ac.els-cdn.com/S1877050918300358/1-s2.0-S1877050918300358-main.pdf?_tid=486a97ac-a49b-42fa-ac01-04dc5ffa4b9a&acdnat=1532023084_2cac69453106815853b7c6fee0ea4d82

  if your interested in our published research material (super technical…)  see here: http://www.artificialgeneralintelligenceinc.com/current-published-research/

Sustainability – Divi is an Eco Friendly Cryptocurrency

What does this mean, an eco-friendly cryptocurrency? The mainstream media has picked up on the fact that the “mining” of Bitcoin and other cryptos use massive amounts of electricity worldwide. The amount is so large that it’s been projected to be more than many medium-sized countries. And growing.

Massive Warehouses Full of Mining Chips

This is happening because of the “Proof of Work” algorithm…

What does this mean, an eco-friendly cryptocurrency? The mainstream media has picked up on the fact that the “mining” of Bitcoin and other cryptos use massive amounts of electricity worldwide. The amount is so large that it’s been projected to be more than many medium-sized countries. And growing.

Massive Warehouses Full of Mining Chips

This is happening because of the “Proof of Work” algorithm that Bitcoin, Ethereum, and many other cryptocurrencies use when building their blockchains. There are now massive warehouses around the world burning huge amounts of power to solve the mathematical equations that are required to win the awards that come with adding a new block to the blockchain. Every few months, better and faster mining hardware is produced, mostly in China, in a never-ending war to solve these equations faster than competitors and share in the Bitcoin bounty.

The Alternative to this Mining Madness

Another algorithm exists called PoS (Proof of Stake) that Divi harnesses to do the same job as mining. Our coin holders can set up either a Masternode or a Staking Wallet to support our network, and are rewarded with more DIVI coins just like in mining, only it’s called minting instead.

Power Consumption:

Laptop: 105 kwh per year with screen 36 with regular use

Antminer: 15,000 kwh per year

So how much electricity is saved? It turns out that Divi’s PoS consensus method saves over 99% of the power, compared with “mined cryptocurrencies”

Reposted from here: https://blog.diviproject.org/eco-friendly-cryptocurrency/ 

By: Geoff McCabe

(Provo, UT)  The AGI Laboratory released a new modified Plutchik model which acts as the underlying basis for biasing ICOM AGI systems.  The lab has used several variations but given various factors is moving ahead with all the research program’s using this model which inverts the emotional valences of the model 360 degree’s making it easier for the underlying system todo baselines and comparisons.  This will show up in forth coming research.

to quote the resent ITSC/IEEE paper on the ICOM theory of consciousness:

“The Independent Core Observer Model Theory of Consciousness (ICOMTC)

At a very high level, ICOM as a cognitive architecture (Kelley 2016) works by streaming data and context processed by the underlying system (the observer) and based on emotional needs and interests and other factors in the system, these are weeded out until only a certain amount are processed, or ‘experienced’ in the ‘core’ (or global workspace) which holds emotional models based on Plutchik’s (Norwood 2016) work.  These elements of the core exist for both conscious and subconscious emotional landscapes of the system where the context that is ‘experienced’ from the standpoint of the system is the only ‘experiences’ that the conscious system is aware of.   In this way, only the differential experience matters and the system, for example, doesn’t understand a word as much as it feels the emotional context of the word as it relates to underlying context.  It is the emotional valences associated with things that the system then selects things to think emotionally about.  The system select’s actions based on how they improve the experiences of those emotional valences and in this way the system may choose to do something logical based on how it feels about it, or it could just as easily pick something else for no other reason than it feels a bit better about it.  In this way, also the system does not have direct access to those emotional values nor is a direct function of the algorithms, but it is an abstraction of the system created by the core that can be considered emotionally conscious or self-aware being sapient and sentient in the abstract.”

This really goes to the fundamental nature of this model as it relates to the ICOM cognitive architecture and why it has the profound biasing effect that it does.

Feel free to use this diagram with references to this work.

References

Kelley, D.; Critical Nature of Emotions in Artificial General Intelligence; IEET 2016; https://ieet.org/index.php/IEET2/more/Kelley20160923

Norwood, G.; Deeper Mind 9. Emotions – The Plutchik Model of Emotions; http://www.deepermind.com/02clarty.htm 403 (2/20/02016)