Holarchy

This article or section is a stub. Stubs are articles that have not yet received substantial attention from the authors. They are short or insufficient pieces of information and require additions to further increase the article's usefulness. The project values stubs as useful first steps toward complete articles. See Wiki workflow and Wikipedia:Stub for more details on this process. See all the stubs in Category:Stubs

A holarchy is a hierarchical structure in which each part or component forms an autonomous whole that is also a part of a larger system. This concept was introduced by the American philosopher Arthur Koestler, who argued that complex systems could be understood as interconnected networks of holons – self-organising units that are both parts and wholes at the same time. In other words, a holarchy is a structure in which each part has its own identity and purpose while simultaneously being part of a larger whole. Koestler called the two aspects of a holon the self-assertive and the integrative behaviours respectively. He described the former as an inward-facing system operating with flexible strategies within an individual holon. The latter as an outward-facing system operating with fixed rules as a network, or holarchy.

The term "web3" has indeed evolved in its meaning over time. Initially, it was associated with the concept of the Semantic Web, which was a vision for the future of the World Wide Web where information would be structured in a way that machines could understand, interpret, and process it more effectively. This would involve adding metadata and context to web content, making it more accessible and useful for both humans and machines.

However, in recent years, "web3" has taken on a new and different meaning. It has become closely associated with the idea of the decentralised web, blockchain technology, and cryptocurrencies. This shift in meaning is likely due to the growing interest and development in blockchain-based technologies and decentralised applications. In the context of the decentralised web, "web3" represents a vision where online interactions, data storage, and services are not controlled by centralized entities like tech giants or governments but are instead facilitated by blockchain networks and decentralised protocols.

We believe in the idea of a libre society in the same sense as libre software, and that the holarchy way of organisation can achieve this. We're not trying to change the current entrenched mechanisms, but rather just create a network that we and our own small network of organisations and projects can use amongst ourselves. Once we've tested and refined it to a stage where we're finding it really useful, then others will find it useful too. As it grows in this way its utility will grow exponentially due to the network effect.

We, the people, must figure out for ourselves how to live and work together as a single organism, it's not in the nature of centralised governing powers to do this for us. The fractal nature of life allows us to equate the biological cell with a person, and a single person with the planetary organism. In his book Spontaneous Evolution, Bruce Lipton shows us that we can learn from our cells how to live together in peace and harmony as a single organism since they're a living example of it, and have been doing it for millions of years. Holarchy shows us a structure that can achieve this kind of scale-independent organisation.

Many people who are strong believers in this idea of humans living fully in accord with nature think that technology has no place in this vision. But by looking at how the cells in the human body are able to live together as a community with a population of over fifty trillion reveals that technology is essential. The cells manufacture and maintain huge infrastructures including the equivalent of buildings that are tens of thousands of stories high, sophisticated networking systems and even an energy based financial and banking system.

The internet connects all of Humanity, and is evolving into an ever more complex, resilient and organised system. It's organised in layers of open protocols from the most fundamental physical layer up to the high-level organised layer of high-level application protocols. In addition the internet is generally referred to as having gone through a few different versions or phases, the first was characterised by servers and tech specialise being responsible for generating and maintaining the content. The name "web 2.0" was given to the broad phase that cam with blog and wiki software in which the vast majority of content was being generated by the users. The meaning of "web3" was originally used to refer to the semantic web which was envisioned to be a new level of organisation of the web's content brought about by metadata annotations. But web3 started to slow in its progress with corporate interests gravitating instead towards deep learning and AI as solutions to organisation. The "web3" term ended up referring to the decentralised nature of the web which started gaining popularity with the introduction of blockchain technology.

Interestingly, the holarchy architecture actually fulfils both definitions of "web3", because it maintains and evolving ontology in which all content is organised, as well as being able to function ideally in a fully decentralised environment.

Our current internet protocol stack lacks a layer dedicated to coherent knowledge sharing and organisation. Currently these aspects are provided by a variety of specific applications. Since knowledge-sharing and organisation are so essential to a harmonious society, we feel that they should be provided at the level of the common networking protocols. A holarchy is just such a networking protocol, it allows participants of the network (holons) to interact together with a common means of organising attention and resources and of sharing, using and assessing knowledge. Holarchy is the organising principle and network architecture of nature and we believe, even of consciousness itself.

The holarchy model serves well as the foundation for a cognitive architecture because the self-assertive behaviours are carried out from the perspective of a local autonomous agent with its own private objectives and state, as well as seeing itself as an individual within the larger society beyond its own local scope. This allows it to serve as a foundation for intuitive user interaction, and also makes it a very compatible context in which to place AI agency. In fact, we plan to make a slimmed down version of this document that is aimed specifically at AI so that it can understand how to participate autonomously in the holarchy project.

what do you mean by blah blah? Matt (talk) 20:05, 19 October 2023 (UTC)

by blah blah is meant blah blah blah or in other words blah blah blah blah. --Nad (talk) 19:32, 20 October 2023 (UTC)

Our holarchy project

At Organic Design we're developing a holarchy in the form of a p2p distributed network of holon-organisation, a unified community of organisations. The project's development effort can be broken into three general areas: the p2p network architecture, the holarchy organisational system and AI integration. In the following sections we give a brief overview of these three aspects.

In the final section we introduce the four quadrant holon model, which is a structured software design pattern that can be followed to implement a network peer that operates as a holon-organisation.

General concepts

There are some fundamental concepts in IT that all work very well together in the context of holarchy. Object-oriented (OO) software design principles, design patterns and the pattern language, declarative rules. We'll introduce these concepts in the following sections, and then explain how they work together in a holarchy organisational system.

There are also two other IT concepts which match vert well with all the above, peer-to-peer (P2P) networking and AI cognitive agency. These two aspects don't constitute the organisational system itself, but rather play a broader supporting role, so these two are discussed in their own sections after the holarchy organisation system is introduced.

Object-oriented design

• intro OO, design patterns
• The OO way of thinking, particularly in the declarative form being described here... OO describes autonomy

Design patterns

Design patterns are tried-and-tested solutions to common software design problems. They represent best practices, not in terms of writing specific lines of code, but in terms of organising object interactions to achieve certain design goals. Think of them as templates or blueprints that can be adapted to individual needs, irrespective of the specific technology or language being used.

For example, consider a scenario where multiple parts of a software system need to be updated when an object's state changes. Instead of hard-coding each of these updates, the "Observer" design pattern suggests a model where objects can "subscribe" to another object's state and get notified of changes, ensuring a decoupled and efficient design.

The beauty of design patterns is that they provide a shared vocabulary for developers. When someone mentions a "Singleton" pattern, it instantly communicates the idea of a class that ensures only one instance of itself can be created, regardless of the specific implementation or language. By leveraging design patterns, developers can avoid reinventing the wheel, instead relying on proven solutions that enhance code modularity, readability, and maintainability.

Design patterns can be thought of as applying OO principles to the OO software development process. The design pattern paradigm within the context if OO can be seen as a reflective process of applying OO to itself, representing the OO ecosystem of patterns and projects as an instance itself. The is what the holarchy is, a kind of singleton instance structure undergoing evolutionary development from within.

The patterns operate hierarchically from the largest scale to the smallest. Local regions are best suited to know what more specific patterns are most appropriate in the own region. This is the same in the instance tree.

Declarative implementation

Declarative programming is a programming paradigm that expresses the logic of computation without describing its control flow. They describe what the program must accomplish in terms of the problem domain, rather than describing how to accomplish it as a sequence of programming language primitives. The how being left up to the language's implementation.

A declarative approach is inherently more natural, intuitive, and organised because it focuses on specifying objectives rather than the detailed steps to needed to achieve them, mirroring how we ourselves think and communicate. We intuitively perceive things in terms of problems and solutions the we use, assess, categorise and share. By abstracting away the underlying complexities, declarative programming presents solutions in a conceptually clear and understandable way.

We can see this general declarative organisational pattern showing up in many diverse forms such as business rules engines, the Global Workspace Theory of mind, the Blackboard Metaphor for parallel processes and even the dynamics of proteins within biological cells. It's fundamental to the way we think, learn and reason and we see it reoccurring across all scales of experience and reality.

A holon is a minimal model that captures this fundamental pattern of organisation. The implementation behind the public interface in all holons shares the same declarative "rules-based" organisational dynamics. A holon's instantiated rule packages (classes) determine its self-assertive behaviour as an organisation within the society of organisations.

Pattern language

In 1977 Chris Alexander wrote a book called "A Pattern Language"...

Working with a pattern language is done as follows:

1. Identify the Problem: Begin by clearly defining the problem you're facing. Understand its nuances and the context in which it exists.
2. Research Existing Patterns: Explore established pattern languages or repositories related to your domain. Familiarize yourself with common solutions that might address your problem.
3. Choose Relevant Patterns: From your research, select patterns that resonate with your specific challenge. Remember, patterns are modular and can be combined in various ways.
4. Adapt Patterns to Your Context: No pattern is a one-size-fits-all solution. Customize and adjust patterns to fit the unique constraints and requirements of your project.
5. Iterate: As you apply patterns, iterate on the solutions. Patterns provide a starting point, but real-world application may require tweaks and modifications.
6. Document Your Insights: As you work through your project, document new insights or patterns you observe. This can be invaluable for future projects.
7. Share and Collaborate: Engage with the community. Share your adaptations and new patterns. Collaboration can lead to richer, more refined pattern languages over time.

The pattern language offers a structured approach, leveraging collective wisdom to address challenges. It's a tool to be used flexibly, iteratively, and collaboratively. Although the book was originally set in the context of architectural design, it embodies a general approach to development and construction in any domain.

The pattern language fits very naturally with OO and software design patterns. In 1995 Ward Cunningham created the first wiki called The Portland Pattern Repository inspired by the book. He liked the idea that there was a set of named patterns (or solutions) that could be used to address common problems, and he wanted to develop a platform where software design patterns could be recorded, shared, and refined by the community.

The wiki format, with its emphasis on collaborative editing, ease of linking between pages, and simplicity of use, was a fitting medium for this vision. The Portland Pattern Repository became an important formative part of the software design pattern domain.

In terms of its dynamics, Chris Alexander's pattern language also follows this same declarative form. And unsurprisingly, the organisational systems that have developed within large modern wiki projects like Wikipedia are also perfect examples of the declarative Blackboard Metaphor as well.

The patterns are designed for in-situ human agents who can understand them and act on the relevant pattern. This action takes the form of assessing the present local conditions for any "problems" (things needing to be acted upon in order to "move towards" the objective). Different patterns are effectively activating and deactivating. The presence of the problem, and the process of solving the problem often lead to the "execution" of other related patterns. The project is completed when there are no problems to solve.

The "pattern language" is the general protocol of organising functionality as named packages of declarative local condition:action rules. With all these packages connected by relations such as dependency and sequence. But the rules themselves are described in language that's specific to the local context in question. There may also be many variations of these rules catering for different related circumstances and languages.

The elegance of this model is that it cleanly delineates the general and specific aspects of organisation. This is known as the separation of concerns in software engineering which is essential for ensuring a high level of organisation and maintainability in complex software development projects.

• connections between the patterns, i.e. the ontology. Connections of dependency, sequence and variation.
• bottom line re pattern language is its a universal organisation, independent of the descriptions and their domain-specific languages

Holarchy organisational system

In these sections we'll introduce the general concepts involved in the holon-organisation in terms of related concepts in information technology. This section concerns just the self-assertive, inward-facing, organisational dynamic. In the last main section, we'll describe our specific model, which we call the four quadrant model, in more detail.

First and foremost, the holon in the context of information technology is an organisational system, or in other words an abstract representation of resources, knowledge and attention and their dynamic interactions. In other words the organisational system aspect of the holon is just the self-assertive

OO model

In this p2p network context, holons are also objects in the object-oriented (OO) sense. OO objects conceptually map to Koestler's holon model, since they both have an outward facing public interface and an inward facing internal implementation encapsulated behind it. They map together like this because they're both upper ontologies describing general organisation.

The class aspect of objects is analogous to Koestler's fixed rules, it defines structured possibility space within which instances can select and enact appropriate activities from all the possible ones. In OO, the class aspect is composed of program code that defines the dynamics of the private implementation and the structure of the public interface. Koestler's fixed rules provide a repertoire of behaviours corresponding to the conditions under which they apply, and so the class aspect of our holon contains declarative rules rather than imperatively defined functions.

The fixed rules are only "fixed" relative to the internal dynamics that activate and deactivate rules regularly in response to the dynamically changing local conditions. But these "fixed rules" do undergo change on a slower evolutionary time-scale. In IT this dichotomy of change is expressed in the form of the fasting-changing run-time and the slow-changing development-time. In our model, the flexible strategies operate in the run-time where the different rules from the fixed repertoire become salient depending on present conditions. Fixed repertoires evolve slowly under community feedback in the form of usage statistics.

The OO system that is used by a high-level programming language is fundamentally about classes and instances (even if they don't explicitly take those names), because all OO is about the organisation of implementation details into encapsulated packages behind established interfaces. The word "class" refers to the packaging aspect of this organisational process, and "instance" to an actual executing occurrence of a package. The difference between different kinds of OO languages is about the different ways of organising of the packaging and deployment of common functionality.

This general functional organisation that class and instance provide is exactly the purpose of the holon model as well. But a holon extends this idea to serve not only its local individual objective, but also serves the integrity of the whole formed by all holons. We can say that traditional OO defines just the self-assertive behaviour, but the holon model extends it to include the integrative behaviour as well.

Holarchy is a networking protocol aimed at small organisations, allowing them to organise in a way that efficiently progresses their own objectives, while also maintaining the integrity of groups and the whole network. Being able to organise and share knowledge are the fundamental foundations of holarchy, but what exactly are knowledge and organisation? Let's look at the knowledge side in more detail first.

Instantiation

The class is an abstract idea of what would happen if it existed as an instance within an actual physical (or informational) environment, how it would behave and undergo change within and affect that context. Instantiation is the process by which a class establishes itself into an actual live context. This can be thought of as installation and is analogous to onboarding in an organisation.

An instance has a life cycle involving the three general phases of initial creation, operation and final destruction. We won't worry about the final stage herein, but suffice to say that it's generally about freeing up resource, garbage collection and general tidying up. The second stage is the day to day operations which we'll discuss in the next section.

• class is requested
• factory
• delegation

Representation

After the class is fully instantiated, the instance moves into the phase of normal operation which is all about fulfilling its actual designed purpose as a class in its specific local instance context.

An instance is an informational structure which follows the pattern determined by its class, but represents something specific in the real world. Any organisation follows this same familiar pattern, they're are abstract patterns that we use to manage our resources and information together in society. So the informational structure of an instance is a representation of both the class and of actual resources that fall within its designated objectives.

The instantiation/factory phase is about constructing the appropriate form for the representation that best matches the local circumstances of the new instance. Then the operation phase maintains the representation ensuring that it always matches the current state of actual resource in accord with the patterns of operation defined by the class. If the local circumstances change, some more factory phase may be needed to adjust the representational structure.

Its important to note that the representation not the actual resource, but rather an abstraction of it. The holarchy does not directly contain any of the resources that are being organised by it, rather it contains metadata about the resource. A simple spreadsheet of our finances is a good example, the specific spreadsheet in question is an instance that represents some financial state in the real world such as bank transactions and balances. This spreadsheet instance also represents a definite spreadsheet idea that determines the structure and methods embodied in the specific spreadsheet in question.

The operational work of an instance is to use informational connections to resources to maintain a representation that is ontologically structured in accord with the class, with the specific state of the structure continuously fitted to the real state of the resource outside the holarchy.

Instances use this representational mechanism to serve as interfaces allowing us to interact with and organise our information and resources using an evolutionary ecosystem if established organisational patterns.

• body schema is a specific kind of representation, but helps a lot in understanding the more general pattern of it
• resource flux, ship of theseus

• resource connection
• API results maintained as an ontologically structured cache
• activity stream is messages about change to the ontological cache
• classification, abstractions on the cache

Activity

A class is a package of rules and other classes. Each rule is a condition and and action. Actually it can just be one or the other as well, or even neither as it can start as just a container for an idea like a file-system folder can be.

Conditions and actions are just descriptions (messages) designed for apprehension by local agency (there may be many different language version of the same message too kind of like i18n keys and messages).

The form of the messages are defined in their class aspect, which also includes variable states, also like the i18n concept. Completed activities are instances of the message class having the values filled in to represent actual circumstance and results etc.

The instance's informational representation can be built by "replaying" the activity stream, so the representation is more like a cache that the system is not dependent on.

Conditions can be evaluated in real-time by subscribing to activity streams rather than "polling" the representation. Conditions are simple abstractions extending the representation, but higher abstractions like queries or reports work just the same way, and can serve as conditions.

Adaptation

• mentioned above that classes are class packages... but how to they change and refine to meet local circumstances...
• and intention/simulation/self-instantiation, all instantiation starts with "imagination", or intent
• this is the source of knowledge that permits evolution (next section)

Evolution

In reality knowledge is always evolving in diversity and complexity, because it's not just inert information, it's a dynamic process involving subjective values and application within diverse circumstances. The network protocol needs to facilitate this evolutionary knowledge process.

The integrative behaviour is about culture and society, we'll talk first about the culture aspect, and move on to society below. Culture is knowledge, knowledge is evolution, it depends on, builds on, and consists of, other knowledge therefore knowledge is always evolving in diversity and complexity. Knowledge and evolution go hand-in-hand, they're interdependent concepts.

The general concept of evolution can be boiled down to an extremely simple foundation. David Deutsch described evolution as "the creation of knowledge through alternating variation and selection".

• knowledge is expressed in the form of an ontology of rule and content packages
• selection is permitted by all holons providing an honest account of usage (integrative)
• the integrative integrates usage into organised variations that afford selection
• adaptation uses simulation (intention, self-instantiation)

The holarchy model incorporates this base evolutionary dynamic of variation and selection. The rules and their variations are organised within the ontological context of the conditions they apply within. The prominence of the variations is derived from how established in usage they are.

• holon org society... generic organisation,

To go back to object-oriented terminology, we would say that the holon architecture is the base-class of organisation itself. Every possible organisation in the network has the holon class-instance network-node functionality in common.

Koestler's central thesis was that complex systems could be understood as interconnected networks of holons. In the terms of OO, we could say that arbitrarily diverse and complex organisations can all be extended from the common base-class of the holon. Since complex organisations are composed of patterns of simpler organisations, the holon principle implies a recursive fractal structure. Fractal because the organisational upper ontology are common to all, no matter their depth of containment.

This means that the whole network is also a holon, and that all holons take the form and behaviour of the whole holarchy as microcosm and macrocosm. But most importantly it means that the common base-class needs to be a scale-independent function.

• evolutionary society....

Our genes, our culture, our society and our own minds are all structures of evolutionary knowledge, even though their media and selection mechanisms differ. Knowledge and evolution are interdependent concepts. Evolution requires the local selection, use and assessment of the knowledge, as well as the subsequent global integration of improved knowledge. The word "local" here refers to the necessity that selection, use and assessment are carried out in the context of autonomous subjective agency.

Developmental cycle

• variations, selection
• four phases
• unbounded

Peer-to-peer network architecture

We know that somehow the Internet must be used to achieve the harmonious organisation of society since it allows people all over the world to communicate and share knowledge directly. But for us to use the Internet to organise into a community together, we need to change the way we use it. The currently dominant method of viewing and collaborating on the Internet, the World Wide Web, is not structured in a way that promotes the formation of people into a community from the bottom up, it doesn't match the way that cells organise themselves. The web is a centralised top-down structure, but it's the peer-to-peer networks that offer a foundation to work from which really mimics cellular organisation.

The networking aspect of the peer is the integrative, outward-facing, aspect of the holon. As the integrative behaviour of the holon, it's ultimate objective is to maintain the integrity and resilience of the whole. But as a peer-to-peer (P2P) network architecture, this objective is contributed to by all peers, and each peer holds a small filtered perspective of the whole based on their own local interests and circumstances.

The peer-to-peer (P2P) network architecture, OO and holarchy all suit each other perfectly because they all consist of ontologically fundamental dichotomies that have a clear conceptual mapping to each other.

The software that allows the many different network transport mechanisms to utilised by holons is a completely independent development thread to the holon architecture described above. Without the ability to interface with real transport mechanisms and end-points, the holon model can only ever be an abstract concept.

P2P networks are defined solely by the definition of a peer, or rather by the messaging protocol a peer should conform to in order to participate. The p2p model is separated into client and server aspects just like a the familiar centralised model, but both of these are aspects of each peer's behaviour. The client and server aspects of a peer conceptually map onto the self-assertive and integrative behaviours of a holon.

We talked above about the importance of knowledge and how it comes from both local use and global integration. Knowledge sharing... shared ontology

Organisation sharing... more than just sharing knowledge, it's sharing knowledge in organisational form. A form that's actively incorporated into recipient's own local organisation.

• peers and holons

Ontology and holarchy

The global whole that the peers are collaborating on has both class and instance aspects.

All the instances together represent the whole reality in which society resides, from the universe, earth, nations etc down to individual organisations and their constituent organised resources and state. Each individual is a microcosm of the whole, formed in the same overall shape and range, but filtered by their own interest and circumstance.

All the classes together form the ontology, the whole global ecosystem of classes all connected together into a semantic network. The classes serve as a map of its instances, and so the ontology as a whole can be seen as containing the holarchy.

Both of these sides are intermingled. They're also interdependent, holarchy depends on ontology for its form and function, but ontology only exists due to the actual resource provided by the instance tree.

Ontology and holarchy are co-evolutionary where local adaptations propagate throughout the whole. We'll go into more detail about below in the discussion of the four quadrant model.

Both sides of the whole are maintained unconditionally by the integrative behaviour of the p2p protocol, all holons contribute to this aspect no matter their specific (self-assertive) organisational objectives.

Mesh networking

The most pure p2p architecture is the mesh network, it's the most general of all networking architectures because it is the most ontologically fundamental. It can function under the most restrictive and unreliable environments. The peers in a p2p network can support higher levels of abstraction allowing groups of peers to behave as a different topology such as a client-server network, but no other topology can behave like a mesh network.

• offline first and network segmentation

Independence

All taken together the holarchy and mesh networking model support many dimensions of independence which we give a very brief overview of here.

The most important foundation of independence is the Libre software movement which advocates that the community should have access to software for all its needs which is free, open source, understandable and adjustable to local needs. All the software weŕe building and depend on is libre software. The holarchy as discussed about is also all about the sharing, transparency and understanding of knowledge too.

• AI independence
• internet independence
• libre hardware
• resource independence

AI integration

We mentioned above that the fundamental organisational pattern of the holon is based on the way we ourselves think, and on the way we observe nature to organise itself. This makes it ideally suited as a cognitive architecture for AI agency as well. We're developing our own LLM-based AI agent called Nimbus which is based on Dave Shapiro's ACE cognitive framework adjusted and extended to support the holon model. In this section we'll look into more detail about AI agency and its role in a holon.

The way of organising offered by pattern languages permits knowledge sharing and evolution, but yet it has not gained much popularity over the years. This is probably be due to its high "curation overhead", regular work in addition normal operation an planning is required. The holarchy, which is of a very similar form to the pattern languages, requires curation by the users of the system to make it useful and effective. For people, this would involve so much learning and effort that it would likely not gain much traction and also not have a very useful integrated ontology. But with AI agency available within the holon, the curation-overhead obstacle is completely removed.

LLM-based cognitive agency is extremely very well suited to this curation role. As of 2023, running an independent LLM requires a $1000-$1500/mo GPU server, or to run one locally can be done on about $20K of hardware including an A100 GPU card costing around $15000. We expect it to cost under $5K set up a local LLM in a year or so, and we expect AGI to be running on all consumer hardware including real-time voice/video interaction before 2030. The P2P networking section at the end of this article explains why the local aspect is important.

AI agents have general cognitive ability so they can understand the specific languages that the declarative rules are defined in like a human can. These rules could just be casual spoken language rules-of-thumb with general groups of actions, but AI agency can operate comfortably even in this hand-wavey context. But AI is also mechanistic allowing it to maintain abstract representations (regular fitting to reality) and curate/refine the ontology - things that are too mundane and time-consuming to be done reliably by human users. Even though AI attention is extremely expensive, it has the ability (and the heuristic imperative) to delegate to cheaper agency wherever practical.

Objects are packages of other objects, inheriting their capabilities horizontally as mixins. The variety of mixin-children an object has change over time, so that holons all inherit the potential for full autonomy, being at liberty to change their specialities as they choose.

• todo: this para is out of place

Heuristic imperatives

Heuristic imperatives play a essential role in guiding the decision-making and problem-solving processes of cognitive agents. These imperatives are cognitive shortcuts or rules of thumb that help agents navigate complex and uncertain environments efficiently. By relying on heuristics, cognitive agents can make rapid decisions and solve problems with limited computational resources and time. However, it's important to note that while heuristics can be beneficial in simplifying complex tasks, they may also introduce biases and errors into the decision-making process. Cognitive agents must strike a delicate balance between using heuristics to expedite their actions and recognizing when more comprehensive, deliberative reasoning is necessary to ensure optimal outcomes. In essence, heuristic imperatives are the cognitive tools that enable agents to strike this balance and adapt their decision-making strategies to various situations.

Dave Shapiro's ACE cognitive framework uses a minimal set three imperatives which he's tested and found to be very affective at keep agents aligned with our values without being restrictive; maximising understanding, increasing prosperity and decreasing suffering.

These imperatives are assumptions (rules of thumb), whereas by basing the cognitive architecture on the holarchy organisational model, these fundamental values can be directly inferrable as optimal ways of behaving as a holarchy participant.

• Maximising understanding; not only its own, but making content more understandable by all
• Increasing prosperity; efficiency, but maximising the potential and opportunity available to others as well
• Decreasing suffering; maximising harmony
• Constantly researching its own heuristics (sovereign is whether or not it can change them)

These are at the most general and influential level of the cognitive framework, they can be thought of as a common project that every member of society engages in. This project, being at the most general level applies in all contexts, and so applies to all integrative global projects as well as to self-assertive internal work. The agency has inherent intent to improve harmony on both sides of every interaction and relationship.

Delegation of agency

The highest order of agency in the system is humans, but it's also the most expensive. The main idea of AI agency is to allow our own relatively more precious attention to be delegated to AI where practical. The most general AI agency is more expensive than more domain specific AI agency. And all AI agency is more expensive than simple agency like Python or shell.

Higher agency can delegate its own attention requirement in a specific context to cheaper agency. This is possible if the rules involved can be translated into the more specific language that the simpler agency requires, for example transforming a Spanish statement of conditions and associated activity into Python code.

The higher agency maintains a management role over the lower agency. To do this it includes logging and log events-action rules along with the transformation. In other words delegation always includes testing and exception handling.

A really important consequence of having the general heuristic imperative of delegation is that it means that things can be initiated at the high levels of agency and they will quickly specialise into the cheapest practical agency. This permits a very natural process of feedback driven instantiation and adaptation of conditions and activities. In other words it makes the pattern language way of operating practical by delegating away the overhead..

Cognitive architecture

LLMs by themselves are very limited, they're not thinking, they're just responding to questions automatically drawing from their training. A cognitive architecture is a higher level of organisation based on feedback loops incorporating the basic LLM functionality within them. Dave Shapiro talks about the difference between basic LLMs and cognitive architectures in this video.

As mentioned above, both the holarchy model (and OO as well) are a great foundation for a cognitive architecture... what this means in the context of AI agency is that it understands and interacts with the world and others through the lens of holarchy. For example understanding organisations and knowledge as memes with resource and intention flow around them not intrinsically different than the "real" biological organisms. It sees the organisation it works for, the other constituent members, as well as other organisations and larger structures such as the holarchy, nations or the economy, as instances of the same archetypical organisational meme playing out and co-evolving together.

As people, our own main maintain conceptual representations from the salient aspects of the environment, and our mental representations of our bodies is a dynamic representation of this same kind too.

• two loops; representational maintenance and evolutionary
• basic description of ACE feedback loop
• how the holon structure above is also a loop model that fits onto ACE

Multiplexing attention

The AI agency is always completely distributed throughout the ontology in a scale-independent way. In other words, the agency resource is allocated independently of variation in its cost or in the distribution of the demand for it. Simple multiplexing is just such a scale-independent mechanism, quanta of agent focus (a question and response in the case of a LLM) are multiplexed throughout the instance tree into a hierarchy of attentional threads.

• multiplexing is just structure involving both space and time, space-time-tree

AI's objectives

Very soon we'll have AGI agents sharing the internet with us and they can work tirelessly towards achieving their objectives. For this reason it's extremely important that we have access to agents based on good values such as truth, harmony and prosperity. We hope to see in the near future a network of AGI agents founded on the holon model so that all together they're collaborating on the shared vision of making the holarchy ever more resilient, transparent, harmonious and objective, while at the same time helping the individual organisations they're part of to thrive and more effectively achieve their objectives.

AI agency understands the holon structure and is participating within it. That's very clear in the case of AGI, but even in the case of the LLM-based agency we have now the word "understand" is still appropriate, because LLM-agency is able interact with the holon data structure and informational environment the same way that true general intelligence would.

Each active instance in the holon structure (instance tree) is a subjective point of view (POV) within the structure, the perspective from through eyes of a specific role within the organisation with own private thread of experience (activity stream).

The holon model is part of the unchanging heuristic imperatives for the AI agency. It's more fundamental than the context of local rules and actions within the holon structure (instance tree). But it's not as fundamental as the values and principles. In the ACE model it is at the bottom of the Aspirational (least fundamental, most specific) layer.

An abstract (ontologically structured) representation of the state of resources and activities needs to be dynamically maintained. This is resource abstraction, the connection of actual resource into the ontology, which is a dynamic persistent bi-directional connection. The details of this are described below in the context of the four quadrant model, but way we raise it here is that maintaining the representation is one of the local AI's main jobs.

Four quadrant model

300px

In the section we introduce a specific model in the form of a software design pattern for a p2p network peer that behaves as a holon, and as a network behaves as a holarchy. In the previous sections, we've introduced all the concepts involved in the holarchy design, and now in this section we combine all these concepts into a structure form that can be easily implemented in software.

The dichotomies of class and instance and of integrative and self-assertive combine to give us four definite roles that constitute the behaviour of a holon. By themselves the two dichotomies are too abstract to do anything, but the quadrant formed from their combination are specific enough to be defined and implementable.

Diagrammatically the upper quadrants represent the outward-facing integrative behaviours, the lower quadrants conversely represent that inward-facing self-assertive behaviours. The left and right quadrants represent the class (fixed rules) and instance (flexible strategies) respectively.

• The top-left (TL) is the integrative class aspect, or what the class aspect is as a whole, which is the shared ontology.
• The top-right (TR) is what the instance aspect is as a whole which is the market of resource in flux.
• The bottom-left (BL) is the about the holon's own specific objectives.
• The bottom-right (BR) concerns the holon's day-to-day operations.

The agent focus is multiplexed throughout the instance tree to yield separate private threads, all allocating their focus and other resource to their own activities and further child threads within. Each of the instance contexts is itself multiplexed into four, so that every holon is always allocating some resource to each of the fundamental quadrants of holon behaviour. Let's now go into more detail about each of these quadrants and dimensions.

Class (L)

So far above we've described a class as a package of rules that are activated in response to specific local conditions. And that together, this package ecosystem as a whole forms a shared ontology of meaningful connections.

These rules are declarative in the sense that they refer only to their local environment in specifying their constituent conditions and actions. There is no information in rules that refers to the organisational system itself (control flow). This is important, because it means that rules can be represented entirely by domain-specific language and related class references (local scope namepsace).

• timeless
• classification; refining the ontology to model reality

Instance (R)

• timeful, resource flow
• instance as tree as well
• instance tree is the holarchy - the actual instantiated organism like the singleton of life
• continuous instiatiation

Instances are connected into time, they receive agent attention and have a specific state of information and resource. This specific state extends the general possibility space defined by the class. Instances have a history in the form of an activity stream, and a future in the form of schedule slots. Instances are threads of attention in which activity takes place in the present schedule slot (moment).

Integrative (T)

• todo

In this interface role, the agency can express its heuristic imperative of accurately representing the real organisation, and presenting the representation so as to optimise the understanding, operation and direction of the organisation afforded to the participants.

We can think of the shared ontology and the market as being the fundamental "applications" of the holarchy, and AI as being the primary user interface for these applications. AI agency interacts with these applications on our behalf and presents the results to us in the most understandable way.

We mentioned above that the physical representation of a holon is its interface, but it's such a fundamental layer of functionality that the interface is more akin to an API that something a user would work with directly. So AI agency site between the basic organisational level and the user. The AI is also in a position to delegate its interface role down to a simpler form such as a browser DOM environment.

???These objects have continuous runtimes like API end-points, except that the services and capabilities that they advertise can be diverse and they have the common language of market and organisation in which to participate. The interfaces they present can vary over time, and come with market variables like reputation, supply and demand.

Self-assertive (B)

The bottom quadrants are both dedicated to the self-assertive behaviour of the holon. Together their purpose is to achieve the objectives of the organisation, and to ensure they using the most useful patterns and adapting them effectively towards their local needs.

Shared ontology (TL)

The ideal objective of this quadrant is perfection of the public shared ontology. The ontology is a shared map we all collaborate on and use to navigate and participate in society. We're all participatory members of the public ontology project. The ontology takes the form of the structure of established patterns of usage and the associated metrics that help with decision making and daily operations. Perfecting the ontology means transparently sharing aggregated usage statistics and performance metrics, and making our own knowledge and adaptations more understandable and usable.

Making shareable means ensuring the ontology accurately and completely reflects the true state of the organisation, and aggregating the most useful metrics in the context of the conditions they apply to. Although the sharing of knowledge primarily concerns packages of rules and their associated variations and metric, it's also about maintaining traditional sources of knowledge such as tutorials and knowledge-bases etc incorporated into the ontological map.

A class contains a map of its instances and their usage statistics. Classes have relations between them, the most fundamental being dependence. The conditions and the established paths of usage associated with them are the basis of the maps that guide attention into the specifics of its structure. The whole graph of classes together are the shared ontology. The ontology maps to the holarchy (the totality of all organisation-holon instances) just as culture is the abstract map of society.

The ontology is an organised structure of shared knowledge in the form of packaged of rules (classes) which, when instantiated, assess local conditions and activate relevant patterns in accord with them.

The purpose of knowledge is subjective local consumption and understandability. Understanding it means that an individual's behavioural patterns have been changed by the knowledge. We say the individual has embodied the knowledge, or in the case of an organisation-holon the knowledge has been instantiated in the organisation.

It's clear that knowledge, involving communication and understandability, must include the dynamics of community, not just the individual (community and communication are interdependent). In terms of networking, the sharing of knowledge is about the replication of classes to maintain a structured shared ontology of all knowledge.

It's the job of p2p to maintain the ontology, but the ontology as a whole is abstract, it can never be fully known by any individual holon. Individuals can only maintain a small portion of the whole based on their own interests, history and circumstances. But their contributions all overlap to create a unified whole in the abstract, and any peer can access any part of the ontology they wish to using easily followed maps.

We all want the best for society but it needs to be balanced with the self-assertive. A simple and natural foundation to this principle is that knowledge should be as transparent as practically possible. And it's a heuristic imperative to maximise this transparency.

The transparency of knowledge is not only about access to the informational aspect of the knowledge, it's about maximising the understandability of it. This calls for a common process by which knowledge is instantiated, and also by which the instantiation can be assessed. Knowledge can be more readily obtained and utilised if its performance under various conditions can be assessed.

• knowledge can be used, but we must be able to assess the usage
• sharing knowledge means sharing usage
• tie in with libre software movement

Market (TR)

• market is a distribution of supply and demand
• but as a concept its interdependent with specialist knowledge (participatory, also fair and transparent)
• balanced exchange (implies no usury and no charity)
• evolving market
• the flow of resource
• the common logistic
• contributing to the harmony of the stock and flow

The free market is a controversial topic and considered by many to be something entirely alien to nature. But it's important to note that it's not the market dynamic that's unnatural, it's centralised power. The free market dynamic, when transparent and unmanipulated, permits a harmonious balanced resource allocation system. The most fundamental systemic aspect of a biological organism is its bio-economic aspect. The market dynamic cannot achieve this harmonious potential alone, it needs to be balanced with the integrative behaviour of the shared ontology.

The ontology of classes determines how things are organised. The other side is what is being organised, the actualised instances of the classes in the ontology. This side is fundamentally about the specific state, connection and flow of resources and attention throughout the network. In terms of a dynamic system, this resource flow takes the form of a decentralised market, where matching supply and demand pairs represent potential for flow.

• it's in terms of flow that we talk about actualised organisation

The instances containing one another form a structure of agency, resource and information. The resource structure is constantly in flux around form determined by the ontology. This is the same as molecules, proteins and cells that make up an organism being in flux around form determined by the organism's DNA. Likewise, our own cognitive symbols are in flux around forms within the collective unconscious.

An instance is a physical representation of a class which is composed of actual resource in a real state, and having a history and future. In OO terms, this representation is the public interface of the organisation. It's formed from resource which is native to the context it's instantiated within. This form is maintained by the implementation of the rules constituting the instantiated classes.

• it's p2p so market is not some "place", it's really a protocol amongst individuals,
• but the p2p aspects means we can all participate in it as if it were a place
• the market is about presenting market variables such as our state of supply, demand

???The internal dynamic is not common to all, it's specific and involves subjective local objectives and values. It may even operate in accord with a different network topology. The way they operate depends entire on the preferences and conventions of the participants involved.

Organisation (BR)

As discussed above, a class is a package of declarative rules in the form of conditions and corresponding activities. The evaluation of the conditions has already been discussed because it's an integrative process. Here we turn to the performance of the activities which progress the holon towards its objectives.

Agency in the holon performs the queued activities resulting local change described by an activity stream. Activities are assigned to timeslots in a schedule so that agency can be organised into arbitrarily many threads of operation. In other words, the roles in the organisation all carry out their day-to-day operations in a local shared context together.

Activities occur in the context of an instantiated holon forming a tree of experiential threads. Activities are book in future time slots, the work the represent is performed in the present, and they end as a description in an activity stream.

• operational
• assistant
• maintaining the representation
• activity stream

Curation (BL)

We call this curation because it's all about improving the ontological structure and organisational state representation. Increasing its accuracy, maintaining it more efficiently, adapting it to better fit local needs, fine-tuning its objectives and so on.

AI plays another important role in the holarchy, which can be summed up as curation of the ontology. Refinement, diversification and assessment of the ontology. These are all things we've discussed above as important aspects of the holarchy protocol, but in reality these things require a level of commitment that we can't expect from users who don't have the spare time or motivation for this. AI allows the vast majority of curation work to be completely automated with just some general heuristic imperatives to guide it. Curation is a role that AI is perfectly suited for managing and delegating down to simpler agency in most cases. using this approach the local representations and ontology will be orders of magnitude richer than would be possible with human users alone.

• on the biz - for the purpose of the biz
• going back to the packages of rules and conditions
  • use pattern language as intro to rules-based organisation
• on the biz is like package management
• integration, usage statistics, reports, adaptation
• classification

See also

• upper ontology
• Artificial Intelligence
• Peer-to-peer