Re: Artificial Intelligence and Group Deliberation

Hi Adam,

Congratulations on your group[1].  I noted Kim Duffy was involved, we
recently exchanged emails - i plan to ensure a connection with the PCI[2]
folk, in the hopes that it'll be helpful for you.

There are of course differences, between all members of our human family
and our things, whether it be religion or otherwise, not all languages of
prayer are supported now by Unicode/internet, and there are many other
tangible issues that are sadly left without meaningful avenue for lawful
remedy, and/or, peaceful redress, etc...

As such, in my opinion, it remains the case that there is alot to do.

With respect to the functional requirements you've outlined below, there
are different ways people can pursue these goals, depending on strategy and
in-turn what people actually want to achieve, as may sometimes be cloaked
by communications strategies such as doublespeak[3], which can be hard when
committed to acting honourably always.

I am not sure if the self sovereign identity and in-turn also perhaps
linked?  the PCI approach, seeks to recommend processing all communications
via tools such as GPT-4, and what the material implications for any such
sort of ideology may in-turn be...  What i might suggest, is that as an
exercise; try to either review or update - add more information that you
may find, in archive.org, etc. to this spreadsheet[4] provided, that is
designed to work with the timeline[5] as demonstrated[6]; and use that
experience, of experimenting with it, to see how the consequence, or
causality, of peoples choices, have meaningful consequences..  Whether it
be skills that are well developed, vs. those that are unknown, or many
other traits.
Indeed, i believe the  https://www.govstack.global/ work - as noted in the
presentation, particularly as demonstrated in the UAE  example, may be a
good partner for you,
https://play.itu.int/event/wsis-forum-2023-govstack-cio-digital-leaders-forum/

Although - the intention of these works, whilst noting - still yet to
establish quorum, and then enact the process where i act to serve the
members, in that capacity, which is expected to take at least a few weeks
to settle out at this stage, given currently available resources....    It
is nonetheless my view that Human Centric, and Human Centric AI systems,
extending from earlier w3c works on the concept[7], does in-fact have
meaningful distinctions - even though these distinctions are presently only
somewhat able to be made communicable via english, at this stage.

You might also find some of the considerations in the consciousness
timeline[8] helpful.

There is also some notes such as this idea of what they call jarvis[9]. As
i have otherwise raised with the millennium project, and PCI folk; in-order
for it to be considered a form of intelligence, it must serve as an agent
for peace, and therefore also human rights.  below is some information
generated about this topic by GPT, as produced in forming basic initial
drafts as part of my peace infrastructure project works, more broadly.
Therein, if the systems do not support the lived experiences of persons to
be characteristically associated to the concept of peace, then is it really
a form of AGI - Artificial General Intelligence, or is it a form of
Artificial General + [antonym of intelligence[10] and the criteria for
defining whether or not someone has successfully created an AGI system, is
different to the definition sought to be defined by any promoters of
systems, that do not support human rights, peace, etc...

The concept of what people do, matters, is fairly old.  Certainly the USPTO
is unlikely to decommission use of priority dates as part of US policy more
broadly, but is that ideal heard? idk.

as previously noted otherwise; irrespective of what sorts of systems act to
have such an enormous influence on the conscious experience of members of
our human family, it is hoped that a means to ensure human beings can
migrate, that the concept of 'digital refugees' at a minimum, alongside the
need to address the issue of forming some sort of formal digital prison
system, and who should be running the prisons - all parts of the sorts of
things that do need to be interoperably addressed, noting the particular
role of W3C in a far broader ecosystem of stakeholders.

Best wishes,

Timothy holborn

*Q:* What are the values universally shared by all of humanity worldwide?

*OpenAI*:

It is difficult to identify values that are universally shared by all of
humanity, as people from different cultures and backgrounds may hold
different values and beliefs. However, there are some values that are
widely considered to be important and are shared by many people across
different cultures and societies. These may include:

   1. Respect for human rights and dignity: Many people around the world
   value the inherent worth and dignity of every individual, and believe that
   every person has certain fundamental rights that must be respected and
   protected.
   2. Fairness and justice: Many people value fairness and justice, and
   believe that everyone should be treated equally and with respect,
   regardless of their background or circumstances.
   3. Honesty and integrity: Many people value honesty and integrity, and
   believe that it is important to be truthful and transparent in one's
   actions and dealings with others.
   4. Compassion and empathy: Many people value compassion and empathy, and
   believe that it is important to show concern and care for others, and to be
   understanding and supportive of their needs and experiences.
   5. Responsibility and accountability: Many people value responsibility
   and accountability, and believe that individuals should be held accountable
   for their actions and should take responsibility for the consequences of
   their choices.

<https://devdocs.webizen.org/SocialFactors/PeaceInfrastructureProject/#q-define-peace-infrastructure>Q:
Define Peace Infrastructure.

Peace infrastructure refers to the systems, processes, and institutions
that support peace in a society. This can include a variety of different
things, such as:

   - Legal frameworks and institutions that promote justice and rule of law
   - Political systems and processes that encourage dialogue and compromise
   - Economic systems that support equitable development and distribution
   of resources
   - Educational systems that teach non-violent conflict resolution and
   respect for diversity
   - Social support systems that provide assistance to vulnerable groups
   and promote social cohesion
   - Media systems that report accurately and fairly on conflicts and
   promote peaceful dialogue

Overall, peace infrastructure refers to the structures and practices that
help to prevent and mitigate conflict, promote reconciliation and
cooperation, and create a stable and secure environment for individuals and
communities.

here are a few more examples of what can be included in peace
infrastructure:

   - Human rights protection: This can include laws and institutions that
   protect the rights of individuals and groups, as well as advocacy and
   education efforts to promote awareness and understanding of human rights.
   - Security forces: These can include law enforcement agencies, military
   forces, and other security bodies that are responsible for maintaining
   order and protecting citizens from violence and crime.
   - Mediation and conflict resolution: This can include processes and
   institutions that facilitate dialogue and negotiation between parties in
   conflict, such as mediation centers, peace negotiations, and truth and
   reconciliation commissions.
   - Civil society organizations: These can include non-profit
   organizations, religious groups, and other community-based organizations
   that work to promote peace and address social issues.
   - Community policing: This can refer to police programs that focus on
   building relationships with community members and working with them to
   address issues of crime and violence.

Overall, building strong peace infrastructure is a complex and ongoing
process that requires the involvement and cooperation of a wide range of
stakeholders, including governments, civil society, and communities.
<https://devdocs.webizen.org/SocialFactors/PeaceInfrastructureProject/#q-how-would-you-define-the-characteristics-of-human-behaviour-or-an-agent-needed-to-consider-it-peaceful-as-is-distinct-to-wrongdoings-violence-negligence-and-other-moral-wrongs>
*Q:* How would you define the characteristics of human behaviour or an
agent, needed to consider it peaceful as is distinct to wrongdoings,
violence, negligence and other moral wrongs?

*OpenAI*:

There are several characteristics that could be considered necessary for an
agent (whether human or non-human) to be considered peaceful. These may
include:

   - Refraining from causing harm to others: A peaceful agent is one that
   does not engage in activities that cause harm to others, such as physical
   violence, verbal abuse, or neglect.
   - Respecting the rights and autonomy of others: A peaceful agent is one
   that respects the rights and autonomy of others, and does not seek to
   control or dominate them.
   - Seeking peaceful resolution of conflicts: A peaceful agent is one that
   seeks to resolve conflicts through peaceful means, such as negotiation and
   mediation, rather than resorting to violence or aggression.
   - Showing empathy and compassion towards others: A peaceful agent is one
   that is empathetic and compassionate towards others, and seeks to
   understand and address their needs and concerns.
   - Actively promoting peace and harmony: A peaceful agent is one that
   actively promotes peace and harmony, and seeks to create conditions in
   which individuals and groups can coexist in a peaceful and harmonious
   manner.

<https://devdocs.webizen.org/SocialFactors/PeaceInfrastructureProject/#q-describe-peace-infrastructure-technology>Q:
Describe Peace Infrastructure Technology...

OpenAI: Peace infrastructure technology refers to the use of technology to
support peacebuilding efforts and promote peaceful societies. This can
include a variety of different things, such as:

   - Communication technologies: These can include tools like social media
   platforms, messaging apps, and online forums that allow individuals and
   groups to connect, share information, and coordinate activities.
   - Data analysis and visualization tools: These can be used to analyze
   and present data on issues related to peace and conflict, such as patterns
   of violence, human rights abuses, and economic indicators.
   - Mapping and geospatial technologies: These can be used to create maps
   and visualizations of conflict-affected areas, helping to identify trends,
   hotspots, and patterns that may not be immediately apparent.
   - Monitoring and evaluation tools: These can be used to track progress
   and assess the effectiveness of peacebuilding interventions, such as peace
   negotiations, reconciliation programs, and economic development projects.
   - Virtual reality and simulation technologies: These can be used to
   create immersive training and education experiences that teach skills
   related to conflict resolution, negotiation, and other aspects of
   peacebuilding.

Overall, peace infrastructure technology can help to facilitate
communication, cooperation, and coordination among peacebuilders, and can
provide important tools and resources for understanding and addressing
conflicts and promoting peaceful societies.

[1] https://lists.w3.org/Archives/Public/public-cogai/2023Apr/0020.html
[2] https://peoplecentered.net/
[3] https://www.youtube.com/watch?v=Fub8PsNxBqI
[4]
https://docs.google.com/spreadsheets/d/1lyiH_4Ht39Mre2TJB8MJCotFk7jjcFuiowYeyvnNp8k/edit#gid=0

[5] https://timeline.knightlab.com/
[6]
https://cdn.knightlab.com/libs/timeline3/latest/embed/index.html?source=1lyiH_4Ht39Mre2TJB8MJCotFk7jjcFuiowYeyvnNp8k&font=Default&lang=en&initial_zoom=2&height=650
[7]
https://www.w3.org/Search/Mail/Public/advanced_search?keywords=%22Human+Centric%22&index-grp=Public__FULL&type-index=&resultsperpage=100&sortby=date-asc

[8]
https://cdn.knightlab.com/libs/timeline3/latest/embed/index.html?source=1r-bo83ImIEjSCmOFFMcT7F79OnCHDOGdkC_g9bOVFZg&font=Default&lang=en&hash_bookmark=true&initial_zoom=4&height=750#event-consciousness-qm-ai-studies-video-edition

[9] https://www.youtube.com/watch?v=ldfZ1lOSjHg
[10] https://www.antonym.com/antonyms/intelligent



On Sat, 8 Apr 2023 at 08:57, Adam Sobieski <adamsobieski@hotmail.com> wrote:

> Human-centric AI Community Group,
>
> Something that Timothy Holborn said in a recent letter to this mailing
> list reminded me of some thoughts that I had about AI a few years ago. At
> that time, I was considering uses of AI technology for supporting
> city-scale e-democracies and e-townhalls. I collated a preliminary
> non-exhaustive list of tasks that AI could perform to enhance public
> discussion forums:
>
>    1. Performing fact-checking
>    2. Performing argument analysis
>    3. Detecting spin, persuasion, and manipulation
>    4. Performing sentiment analysis
>    5. Detecting frame building and frame setting
>    6. Detecting agenda building and agenda setting
>    7. Detecting various sociolinguistic, social semiotic, sociocultural
>    and memetic events
>    8. Detecting the dynamics of the attention of individuals, groups and
>    the public
>    9. Detecting occurrences of cognitive biases in individual and group
>    decision-making processes
>
> With respect to point 3, a worry is that some participants in a community
> might make use of AI tools to amplify the rhetoric used to convey their
> points of view. These were concerns about technologies like: "virtual
> speechwriting assistant" and "virtual debate coach".
>
> Some participants of an e-townhall or social media forum might make use of
> AI tools to spin, to persuade, to manipulate the other members for their
> own reasons or interests or might do so on behalf of other parties who
> would pay them.
>
> My thoughts were that technologies could mitigate these technological
> concerns. Technologies could monitor large-scale group discussions, on
> behalf of the participants, while serving as tools available to all of the
> participants. For example, AI could warn content posters before they posted
> contentious content (contentious per their agreed-upon rules) and
> subsequently place visible icons on contentious posts, e.g., content
> detected to contain spin, persuasion, or manipulation.
>
> I was brainstorming about solutions where AI systems could enhance group
> deliberation, could serve all of the participants simultaneously and in an
> open and transparent manner, and could ensure that reason prevailed from
> group discussions and deliberations. Today, with tools like GPT-4, some
> of these thoughts about humans and AI systems interoperating in public
> forums, e-townhall forums and social media, seem to be once again relevant.
> Any thoughts on these topics?
>
>
> Best regards,
> Adam Sobieski
>
>