AI Abstract Series Episode 1: Architecting a Human-like Emotion-driven Conscious Moral Mind for Value Alignment and AGI Safety.
Welcome to the Technocracy A.I. Abstract Series for Published Scientific Work in the A.I. and Artificial General Intelligence field.
Title: Architecting a Human-like Emotion-driven Conscious Moral Mind for Value Alignment and AGI Safety.
Peer reviewed by AAAI at Stanford University, Palo Alto, California, March 2018.
By Mark Waser, and David Kelley.
Abstract: A general intelligence possesses the abilities, given any goals and environment, to iteratively evaluate, plan, discover or learn and build or gain competencies, tools, and resources to succeed at those goals. The only known examples of general intelligence are the obligatorily gregarious, conscious “selves” called humans that currently dominate our planet. We argue that human beings are reasonably deep in a safe and effective attractor in the state space of intelligence and that adhering as closely as possible to the human model, particularly in reference to the three cited properties, has the advantages of safety, effectiveness, comfort and ease of transition due to a known and explored state space. Most concerns about AI safety are due to expected differences from humans – which seems silly when not only can we choose to make them more humanlike but the history of AI research clearly shows that we are unlikely to succeed unless we do so. We, therefore, propose a human-like emotion-driven consciousness-based architecture to solve these problems. We rely upon the Attention Schema Theory of consciousness and the social psychologists’ functional definition of morality to create entities that are reliably safe, stable, self-correcting and sensitive to current human intuitions, emotions, and desires.
As always thank you for listening to the Technocracy Abstract Series and a special thank you for our sponsors the Foundation, Transhumanity.net and the A.G.I. Laboratory.
AI Abstract Series Episode 1: Architecting a Human-like Emotion-driven Conscious Moral Mind for Value Alignment and AGI Safety. was originally published on transhumanity.net
(JULY 2017) – At the AGI Lab in Provo we have a number of people working on different things and between everyone there are a number of great things coming out from a number of them including material related to two books, and some peer reviewed papers. The material is in order of release.
BICA (Biologically Inspired Cognitive Architectures) Proceedings/Journal 2017 and Procedia Computer Science has accepted the following paper: Human-like Emotional Responses in a Simplified Independent Core Observer Model System
Abstract: Most artificial general intelligence (AGI) system developers have been focused on intelligence (the ability to achieve goals, perform tasks or solve problems) rather than motivation (*why* the system does what it does). As a result, most AGIs have an unhuman-like, and arguably dangerous, top-down hierarchical goal structure as the sole driver of their choices and actions. On the other hand, the independent core observer model (ICOM) was specifically designed to have a human-like “emotional” motivational system. We report here on the most recent versions of and experiments with our latest ICOM-based systems. We have moved from a partial implementation of the abstruse and overly complex Wilcox model of emotions to a more complete implementation of the simpler Plutchik model. We have seen responses that, at first glance, were surprising and seemingly illogical – but which mirror human responses and which makes total sense when considered more fully in the context of surviving in the real world. For example, in “isolation studies”, we find that any input, even pain, is preferred over having no input at all. We believe that the fact that the system generates such unexpected but “human-like” behavior to be a very good sign that we are successfully capturing the essence of the only known operational motivational system.
IAAA Fall 2017 Symposium Paper titled: The Independent Core Observer Model theory of Consciousness and the mathematical model for Subjective Experience
Abstract: This paper outlines the Independent Core Observer Model (ICOM) Theory of Consciousness defined as a computational model of consciousness that is objectively measurable and an abstraction produced by a mathematical model where the subjective experience of the system is only subjective from the point of view of the abstracted logical core or conscious part of the system where it is modeled in the core of the system objectively. Given the lack of agreed upon definitions around consciousness theory, this paper sets precise definitions designed to act as a foundation for additional theoretical and real-world research in ICOM based AGI (Artificial General Intelligence) systems that can be measured objectively.
Springer Publishing by Newton Lee for an ‘un-named’ book coming out by the end of the year with a chapter: The Intelligence Value Argument and Effects on Regulating Autonomous Artificial Intelligence
Abstract: This paper is focused on the Intelligence Value Argument or IVA and the ethics of how that applies to autonomous systems and how such systems might be governed by the extension of current regulation. IVA is based on some static core definitions of ‘Intelligence’ as defined by the measured ability to understand, use and generate knowledge, or information independently all of which are a function of sapience and sentience. The IVA logic places the value of any individual human and their potential for Intelligence and the value of other systems to the degree that they are self-aware or ‘intelligent’ as a priority. Further, the paper lays out the case for how the current legal framework could be extended to address issues with autonomous systems to varying degrees depending on the IVA threshold as applied to autonomous systems.
AI Safety and Security 2017 Book by Dr. Roman V. Yampolskiy’s book including a chapter for review by Mark Waser covering AI Safety and Security around emotionally driven AGI systems including ICOM – 2017 should be out by the end of the year, book overview includes: “The history of robotics and artificial intelligence in many ways is also the history of humanity’s attempts to control such technologies. From the Golem of Prague to the military robots of modernity, the debate continues as to what degree of independence such entities should have and how to make sure that they do not turn on us, its inventors. Numerous recent advancements in all aspects of research, development, and deployment of intelligent systems are well publicized but safety and security issues related to AI are rarely addressed. This book is proposed to mitigate this fundamental problem. It will be comprised of chapters from leading AI Safety researchers addressing different aspects of the AI control problem as it relates to the development of safe and secure artificial intelligence. The book would be the first textbook to address challenges of constructing safe and secure advanced machine intelligence. ”
* hero image used from http://armytechnology.armylive.dodlive.mil/index.php/category/army-technology-magazine/robotics-army-technology-magazine/ (file marked for non-commercial reuse)
AGI Labs In Provo – Progress Report was originally published on transhumanity.net
Last MTA meeting I sent to I was speaking with Lincoln Cannon about his new company “Thrivious” and their Nootropic stack.
I have been taking a Nootropic stack for some time and have read a lot of material on them. I’ve tried tDCS along with it and Nootropics like Piracetam and Aniracetam on top of the regulat Nootropics all looking for cognitive improvements. I keep a lot of things in…
Last MTA meeting I went to I was speaking with Lincoln Cannon about his new company “Thrivious” and their Nootropic stack.
I have been taking a Nootropic stack for some time and have read a lot of material on them. I’ve tried tDCS along with it and Nootropics like Piracetam and Aniracetam on top of the regular Nootropics all looking for cognitive improvements. I keep a lot of things in OneNote and in the conversation with Lincoln I pulled up the list and found that the research I had done, aligned well with his company’s research in terms of a strong Nootropic stack. I was pleased to see Lincoln starting up a great company and being so thorough. Additionally I was pleased to see that, for the most part, my research and his (his being much more thorough) landed on the same things.
To that end, Thrivious (a new Transhumanist start up) appears to be the best stack on the market for Nootropics.
by buying from this link you support t.net
If you’re into Nootropics like I am I encourage you to amp up your brain… click here buy Nootropics and support Transhumanity.net:
Nootropics and Thrivous – Better Brains Now… was originally published on transhumanity.net
Extreme Futures and Technology Forecasting Work Group - Winter 2017 (March 11th, Provo, Utah)
EFTF and the EFTF Manual is a TNC (Transhuman National Committee) Fundraiser.
Get Tickets Here for the Saturday March 11th in Provo, Utah: https://www.eventbrite.com/e/extreme-futures-and-technology-forecasting-work-group-winter-2017-tickets-28855253841
This is a work group that will be an all day workshop on the EFTF book and replaces the regular winter event.
* if you want to setup a table or sponsor or other interaction with work group let us know
The work group is about getting the book ready and correlating content and for several discussion groups related to forecasting, presentations and related planning for the EFTF 2017 manual. The EFTF program is about helping futurists and technologists work out where we are going and how we might get there and the likely outcome for various technology sectors will see and with the manual provide a method to help others with that process. Conference/workshop attendee’s participate in our qualitative analysis process to produce the Extreme Futures Technology and Forecasting Manual and attendee’s get a copy of the 2017 manual. There will be a number of lighting rounds on different technologies sectors covering AI/AGI, AR/VR, Biotechnology, Space, Wearables and personal technology and much much more.
Also at this event there will be a tour of the Hall labs and some of the elements of the Evolution of Personal Technology Showcase and Device Bar maintained by the conference show casing everything from watches to cybernetic implants or just to plug in your project. The Technology Showcase will be donated to the the Eternity Library by the Foundation when it gets its location in the Utah area.
Some of most exciting equipment that is part of the bar is the actual cybernetic implants, HoloLens, tDCS, and numerous other great wearable technology displays showing our deeply personal relationship with technology.
Attendee’s will become named authors of the Extreme Futures Technology and Forecasting Manual 2017 edition
Imagine a book that predicts the future of technology that evolves with time, trends with unprecedented accuracy designed for technologies, futurists and other analyst.
The compilation will come out each year.
Contributors will get a copy each year they participate where other’s will have to purchase them. All Contributors are named and contribute by attending the various Extreme Futures Technology and Forecasting Conferences where everyone will be contributing to activities we will do during the conference as part of the agenda including the technology forecasting exercise based on the Futures Squares methodology, study group role playing simulations and workshops based on techniques done with DARPA and the US Military and government but this time open to the public w/o government or other oversight skewing results.
Other sections will be briefs submitted and Singularity Index analysis based on the t.net research program measuring stock related to core AGI related corporate investments. All of this formatted in a way to help people look at the key trends and likely outcomes. Everyone will be named directly. The TNC will use it as a key tool in Transhumanist sound policy lobbying and companies will use it to predict viable investment and research programs and more.
Come predict the future…
Attend the EFTF in Washington DC, Support the TNC and Futurist in advancing technology.
That afternoon we will have a tour of Hall Labs, and then a scenario workshop with Dinner at a to be disclosed location.
Current Presenters in morning session, including TNC Chair David J Kelley, TNC Board member Mark Waser, Future Squares Author Adair Daniels,
Opportunities:
Please submit proposals, if you want to sponsor the conference or setup a demo table please let us know.
Sponsors:
http://www.dangerousthings.com/
H+
www.TranshumanPolitics.com – TNC
Transhumanity.net
www.ArtificialGeneralIntelligenceInc.com
please note that due to the fee’s and planning and related costs we are not able to do refunds.
Extreme Futures and Technology Forecasting Work Group – Winter 2017 (March 11th, Provo, Utah) was originally published on Extreme Futures Technology & Forecasting
Extreme Futures and Technology Forecasting Work Group - Winter 2017
Extreme Futures and Technology Forecasting Work Group – Winter 2017
EFTF and the EFTF Manual is a TNC (Transhuman National Committee) Fundraiser.
Get Tickets Here for the Saturday March 11th in Provo, Utah: https://www.eventbrite.com/e/extreme-futures-and-technology-forecasting-work-group-winter-2017-tickets-28855253841
This is a work group that will be an all day workshop on the EFTF book and replaces the regular winter event.
Extreme Futures and Technology Forecasting Work Group - Winter 2017 (March 11th, Provo, Utah)
EFTF and the EFTF Manual is a TNC (Transhuman National Committee) Fundraiser.
Get Tickets Here for the Saturday March 11th in Provo, Utah: https://www.eventbrite.com/e/extreme-futures-and-technology-forecasting-work-group-winter-2017-tickets-28855253841
This is a work group that will be an all day workshop on the EFTF book and replaces the regular winter event.
* if you want to setup a table or sponsor or other interaction with work group let us know
The work group is about getting the book ready and correlating content and for several discussion groups related to forecasting, presentations and related planning for the EFTF 2017 manual. The EFTF program is about helping futurists and technologists work out where we are going and how we might get there and the likely outcome for various technology sectors will see and with the manual provide a method to help others with that process. Conference/workshop attendee’s participate in our qualitative analysis process to produce the Extreme Futures Technology and Forecasting Manual and attendee’s get a copy of the 2017 manual. There will be a number of lighting rounds on different technologies sectors covering AI/AGI, AR/VR, Biotechnology, Space, Wearables and personal technology and much much more.
Also at this event there will be a tour of the Hall labs and some of the elements of the Evolution of Personal Technology Showcase and Device Bar maintained by the conference show casing everything from watches to cybernetic implants or just to plug in your project. The Technology Showcase will be donated to the the Eternity Library by the Foundation when it gets its location in the Utah area.
Some of most exciting equipment that is part of the bar is the actual cybernetic implants, HoloLens, tDCS, and numerous other great wearable technology displays showing our deeply personal relationship with technology.
Attendee’s will become named authors of the Extreme Futures Technology and Forecasting Manual 2017 edition
Imagine a book that predicts the future of technology that evolves with time, trends with unprecedented accuracy designed for technologies, futurists and other analyst.
The compilation will come out each year.
Contributors will get a copy each year they participate where other’s will have to purchase them. All Contributors are named and contribute by attending the various Extreme Futures Technology and Forecasting Conferences where everyone will be contributing to activities we will do during the conference as part of the agenda including the technology forecasting exercise based on the Futures Squares methodology, study group role playing simulations and workshops based on techniques done with DARPA and the US Military and government but this time open to the public w/o government or other oversight skewing results.
Other sections will be briefs submitted and Singularity Index analysis based on the t.net research program measuring stock related to core AGI related corporate investments. All of this formatted in a way to help people look at the key trends and likely outcomes. Everyone will be named directly. The TNC will use it as a key tool in Transhumanist sound policy lobbying and companies will use it to predict viable investment and research programs and more.
Come predict the future…
Attend the EFTF in Washington DC, Support the TNC and Futurist in advancing technology.
