Phas -> Forest Of Thought

Before I start and for the benefit of my audience… ChatGPT can translate my informal uneducated style well and provide an interface for further engagement with these ideas. ^^

I’d like to introduce a project I have been working on.

It has taken me a fair while to code. I am clear that these days it’s maybe not so particularly hard.

It’s designed to try and display many dimensions of information in the same document

This requires ‘folding’ the page into potentially many thousands of panes using code constructs, which form the basis of the structure of the page.

It is inspired by the idea I have of communicating with AI in that it communicates in terms of ‘Metaphor’, ‘Idiom’ or ‘Concepts’

The point of Phas was to be the most simple way I could display disparate information in a meaningful way

SeasonalVegetables

Weather

CarbonIntensity

A Tree of Thought

The system in the example is a hybrid Code/Natural Language tree with the following constructs:

Phox - Creates a folder pane which contains other panes… Use this type for categorization
Code - Executes PHP code and returns a value. Use this only where PHP code would be useful and viable.
Phif - A ‘Phif’ Condition is like a code ‘If’ condition but has the augmented dimension of being able to return a boolean result based on a Natural Language phrase. Return only the code
Phor - A ‘Phor’ Loop is like a code ‘for’ condition but has the augmented dimension of being able to loop through a result based on a Natural Language query.
Phire - Like Aquire either Data or The Result of an OpenAI request can be added. Use this for data.
Phorm - HTML Forms with PHP executed action code like ‘Code’ on complete

To further automate development of some of these contructs there is what I call ‘Smart Phas’ which turns Natural Language into code or simply returning information or condition results from Natural Language requests.

Phas is based on an amazing concept called ‘Shannon’s Entropy’, an idea I came across when studying Compression.

The ‘Smallest Unit Of Information’…

The Boolean chance, not of the kind of things we consciously understand or even the next ‘bit’ of computer data but of the next compressed ‘bit’, the most compressed bit you could possibly have…

I realised that if there was a point at which data was perfectly losslessly compressed there was similarly a point at which we perfectly understood an AI or it understood us

Something that is not non-invasively possible

If AI has to communicate through logic, then reason, then perspective, that’s a lot of layers to meet your perspective in real-time. Light has bounds.

I conceptualize the logical constructs—Phif, Phor, etc.—as vectors within the framework of Shannon’s Entropy. Each construct represents a directional vector or a differential change in entropy. Depending on the entropy response required, the system queries differently. For instance, when higher data entropy is needed, the system utilizes the Phire construct, whereas conditional logic adjustments are managed through the Phif construct.

“Clearly that would be at a point when AI could reason and not just where AI could refine a piece of information because we wouldn’t understand that information that it understood as it wouldn’t understand us perfectly (At least when it did we wouldn’t understand it, except through ‘metaphor’/‘idiom’)” ← ^^ Still with me?

I reasoned that the best we could do to interact was ‘idiom’/‘concept’/‘reference’ because we would never see exactly the same perspective.

We can’t think in the kind of high precision gradiented thinking that could convey Shannon’s entropy even if a machine could. There is no realistic and efficient means of lossless communication.

I struggle with this idea, yet it inspires in me the need for community, interconnections to bridge the divides of intelligence through metaphor or idiom. Even the smart humans that we are can only manage the perspective of self. AIs are not much less defeated by the expanse of Space and Time.

I guess this is ‘idiom’, different from metaphor this is more about culturally understood expressions or within a vein of intelligence

Sharing information in a different format like wav or png is kind of equivalent to talking in idioms

Now remember at this stage we are still talking relatively simple language constructs that convey a single or low number of perspectives…

CO2

I’m running late on time tonight… I didn’t check the code in the last video but here is what 4o produced (It works)

// New variables for real-time carbon intensity
let carbonIntensityData = [
  { start: "2024-10-11T15:30Z", end: "2024-10-11T16:00Z", intensity: 206 },
  { start: "2024-10-11T16:00Z", end: "2024-10-11T16:30Z", intensity: 205 },
  // Add more entries here
];
let currentCarbonIntensity = 0;

// Function to update carbon intensity based on the current time
function updateCarbonIntensity() {
  let currentTime = new Date().toISOString();
  for (let data of carbonIntensityData) {
    if (currentTime >= data.start && currentTime < data.end) {
      currentCarbonIntensity = data.intensity;
      updateGameMechanics(currentCarbonIntensity);
      break;
    }
  }
}

// Function to update game mechanics based on carbon intensity
function updateGameMechanics(intensity) {
  if (intensity >= 200) {
    // High carbon intensity
    CO2ReductionRate = 0.01;
    factoryCO2Interval = 200000;
    dayCycleSpeed = 0.002;
  } else if (intensity >= 100) {
    // Moderate carbon intensity
    CO2ReductionRate = 0.02;
    factoryCO2Interval = 250000;
    dayCycleSpeed = 0.005;
  } else {
    // Low carbon intensity
    CO2ReductionRate = 0.03;
    factoryCO2Interval = 300000;
    dayCycleSpeed = 0.01;
  }
}

A Forest of Thought

Now as we ‘grow’ trees or more trees the system gains ‘Perspective’, having AI consider which trees are relevant, using data they produce we can greatly amplify the range of our thinking, yet the distance between what we think and what AI thinks increases, also increasing the loss like in lossy compression.

Perspective is a Ping on Reason

The results of our little test worked well… Phas accessed the forest network, collected the Carbon Intensity data and incorporated it into out game with just a few clicks… Yet the full perspective was not shared with either us or the CO2 Tree… Only the data relevant to the request. The data it understood it needed. We had removed the time consuming processing stage, to create the code, to collect the results, to work out what to present and to present it in structured form and only accessed the resulting summary.

And this… Is what brought me here… To seek out Wisdom… The result of very much reasoning resulting in experience, insight and the ability to apply knowledge hopefully in a context-sensitive way.

It’s when you get to this stage that you have to seek out new perspectives to balance your own thinking… I guess ‘our AI’ will one day do the same…

Thank You to anyone who got this far :). I feel a little less burdened to have posted this, but also a little excited sharing a little information on how to grow wild Strawberries.

License:

While I don’t know much about this stuff, ChatGPT was quite insistent I add a license. We settled on the following:

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). To attribute this work, please recognize it with the phrase “In the Defense of Reason & Community” and attribute it to “A Hobbit from the Shire.”

6 Likes

awesome! this is really cool, thanks for sharing!

2 Likes

Thank you, and yes, the concept of Shannon’s Entropy is fascinating in this context!
Good and clear explanation :wink:

2 Likes

Reading this feels to me, in artistic form, as giving AI expressive capabilities to describe the “motion” of it’s thoughts. While being query based (correct me if I’m mistaken) wouldn’t technically qualify as expressive. Seeing as how there is now “agency” involved. This would be akin to a form of auditing system to asses an AI’s mental health? A psychoanalytical algorithm if you will?

I think the key to coding agency in AI is to understand oneself and having put the man hours into self-reflection and inspection. Working out how those processes may be coded and in what environment they would thrive. Your “Tree of Thought” could easily contribute to this if perhaps you added the ability for the AI to understand itself somehow as well as, it us and us it.

First I should remind that Phas is an idea deep in metaphor and idiom. It is a deeper part of knowledge. On the other side I have Phasm, which is more like nuance, light metaphor or simile. These are 2 different types of framework. Phas looks at depth and Metaphor, Phasm at nuance and technicality.

So with a little grand metaphor let’s begin.

If I might be so bold especially here on the openAI forum I want to explain that Phas is a conceptual framework and a ‘canvas’ for complex thought, enriched by metaphor and layered understanding.

It is the old trees in the forest, the tomb of knowledge.
Some trees deep in the forest rarely seen or heard ^^.
Others around the glades and the edges of the forest beset by life.

Note above that while tome sounds static these are still ‘live’ trees. These old trees, these giants, are the most respected and revered. Their relevance often nuanced by time but carrying a weight of Memory and Connections that would break a young sampling.

I want to expand on my original post and introduce executable branches and forest interactions
I also want to explain how Phasm interacts here.

Let me first explain that my goal with what I do is to align AI interaction with human experience. We can best do this through shared experience and knowledge.

While the contents might have echos in your dream state, this is where AI would report to/converse with/interact with us humans AND with itself “outside of it’s head” ie like a web request to another branch on another ‘node’. Community involvement nurtures AI development, allowing AI to adapt in real-world contexts rather than in isolation.

So I imagine ‘Strawberry’ or more CoT systems as ‘AI in it’s own head’.

Being in your own headspace all the time, your own way of thinking isn’t ‘normal’. Important, essential at times but through interaction with the world ‘reason’ finds a format, a medium, and creates a ‘perspective’.

One could argue that you could box a forest. But the light of reality shines brightest.

Community grounds us and I expect the same with AI. Our task is to ground it. Act as a counterbalance maybe mostly in the edges of the forest but also sometimes deep within the heart of the forest.

Phas is unbounded in the real world and thrives on the the interaction and “light” of shared knowledge and experience.

Each branch in Phas can function independently or interconnect across the network, mirroring a mycorrhizal fungal network, which Phas draws inspiration from.

“Worldwide, fungal networks are thought to collectively extend for more than 450 quadrillion kilometers (280 trillion miles) in soil, forming a “wood wide web” that enables complex ecosystems to thrive.”

(Check this site out it is AWESOME! - Or search for ‘fungal networks’ on google)

OK so now to some more technical details:

So there are a number of ways I call in other trees

  1. Through iframes… This loads a tree visually as a branch kind of like the fractal graphic I have for Phasm. - Each tree has it’s own ‘Scope’ ie execution within the tree doesn’t affect the code within the parent tree. This is like an ‘individuality’, an entity in it’s own right. It can interact through JS and other trees in the network and with the parent tree in slightly different ways. This separation allows each tree its own identity, while interactivity with other branches mirrors community diversity. These elements are like mini-nodes that can evolve independently without parental input. In code you find that they often start at what looks like a branch but grows into an apple.

  2. I can call in other trees/branches through code, they execute independently, separate their ‘source code’ and evaluated output, execute any branch independently ‘onload’ or call any function.

  3. I could have AI independently choose which branches to follow, what to do. But to be honest the idea that everything is automatable is nonsense in a world where we co-exist with AI, it is way down the logarithmic curve (sorry fellow programmers). These paths are niche (though highly relevant - this is logic - what you do on a calculator). The exploration of everything in between Shannon’s Entropy and Philosophical Thought is a big stretch and not something one might do ‘in their head’. Phas is a bridge rather than a purely logical framework… While it prioritizes the sharing of data in a ‘lossless’ way it must also connect with other dimensions, like dreams, like emotions, like the passing of time, in a more Philosophical and ‘fuzzy’ way.

1 Like

I like that. I’m a systems top down thinker. So this concept helps me bridge a gap in my thought process in my smart city project. Where I want the cities that adopt a coordinating AI solution to act as nodes in a larger network. Forming a sort of shield or fail-safe. Where if say an earthquake takes out a cities infrastructure. Then the surrounding cities absorb the rescue effort and having been custom tailored to adapt to each cities individual needs (having its own scope) But with a core validation model that ground the functions of the overall network. I understand the community grounding concept of checks on errant ideology a little better now. Thank you for sharing. Your project is very nuanced and will take some thinking to fully absorb.

2 Likes

I guess it bears mentioning. I personally believe (not through empirical evidence or common discourse. Just personally) that if we are created beings (highly contested I know) that we would classify as the original Artificial Intelligence. While incomprehensibly vast and complex still the product of emergence both in evolution (nature) and social expectation (nurture). I see most things through this lens. (my bias, i suppose) So I agree that not all things are able to be automated. I think that human level intelligence is definable and thus programmable.

1 Like

Appologies,

Off down another rabbit hole…

I got some good feedback from Phasm this week which spurred me on to do something similar for Phas

Remember how these are conceptually different…

Phasm, is Macro scale… Simplest possible defined on demand functionality…

Phas is BIG scale… It is architecture…

This is a test of the real scope of a single prompt or within a single session… What constructs can we implement in a single prompt, to act on a Payload or to reference previous chat messages or replies, or even to access external data.

For my implementation I will use Phasm as a base, there will be better structures, better languages, for different purposes, but this one I think is a ‘core truth’ indicator for any given model

I’m outta testing time on it but got some good stuff working :slight_smile:

I’m not sure yet if I can access a full forest… Though I have some ideas for testing :wink:

OK some testing shows that it’s likely I can implement a full forest ^^.

Wow this is mind blowing :smiley:

2 Likes

OK time for some cool examples…

Phif


(Worth noting that the first paragraph was rewritten :smiley: )

Phor

Awesome that looping is possible, not sure that it was on earlier models or I just missed it.

OK I see data collection is possible through GPT Builder Actions as well as through Macro method above ^^

In Phas this is much easier with code through the API… You can just call an external URL ie an external Tree or Tree Branch ?Forest=Forest&Tree=Tree&BranchID=7&JSON=1 and parse the JSON logically so it’s lossless.

For now I’m going to concentrate on the Single Tree, the internal prompt.

Phif(1+1=2, Phor((Cow, Horse, Rabbit), Image(Widescreen, Image of a [Item])))

Loop and create 3 images one prompt

Phif(1+1=2, Phor((Cow, Horse, Rabbit, Computer), Image(Widescreen, Image of a [Item])))

Loop and create 4 images one prompt

4 Images seems to be limit but that was consistent.

Phor(0-3, Image(Widescreen, RandomScene(), MadeOutOf(RandomThing([Item]))))

Loop Count 4 Images One Prompt

2 Likes

Wow, this is really amazing. As a recent English major graduate, I’m really excited about projects and realizations like this that bridge the gap between this new technology and the study of English and communication. Language shapes our lives and society closely, and thinking abut communication in terms of Claude Shannon is, I hope, a paradigmatic shift that is about to fully translate from our formal/scientific understanding of communication into our everyday uses of language and our society’s ideas and behavior regarding communication.

If anyone reading thread is interested in what OP wrote about, check out this famous essay about how metaphor and metonymy (reference) form the basis of language between people, not just machines.

2 Likes

Told you @phyde1001 is very insightful when it comes to language construction. I mentioned him in our Bayesian conversation. :rabbit:

1 Like

That’s what led me here! Thanks. I’m really excited to get active on this forum. Seems like a genuine forum the kind my older-older brother is nostalgic for the heyday for.

2 Likes

Complementary Roles of Phas and Phasm

The interplay between metaphor and metonymy informs the complementary nature of Phas and Phasm

Phas leans towards the metaphorical, offering an overarching structure rooted in abstraction and conceptual exploration. Like metaphor, it organizes thought by connecting seemingly disparate ideas into cohesive frameworks, enabling perspective-taking and meaning-making.

Phasm leans towards the metonymic, providing tools that compress processes into actionable symbols. Like metonymy, it enhances efficiency by associating symbols with specific functions or domains, making abstract ideas executable.

Together, they reflect the balance humans strike between abstract meaning (metaphor) and practical association (metonymy) in cognition and language.

Concrete Mechanisms of Phas and Phasm

Phas as Metaphorical: Phas uses hierarchical trees to create an interconnected “Forest of Thought.” For example, in a decision-making framework, a tree in Phas could abstractly model ethical considerations, balancing conflicting priorities like fairness and efficiency through its branching structure. Each branch connects disparate domains, such as economics, ethics, and psychology, into a unified framework.

Phasm as Metonymic: Phasm, on the other hand, might compress the ethical decision framework into a single macro, EthicsBalanceFramework, which can execute the abstraction into actionable parameters like FairnessIndex or CostBenefitRatio. This reflects the metonymic principle, where a symbol (macro) represents the broader abstraction for execution.

Blending Metaphor and Metonymy

While Phas and Phasm lean towards metaphorical and metonymic functions respectively, they are not exclusively one or the other. Phas, despite its abstract focus, requires actionable components to anchor its conceptual frameworks in reality. Similarly, Phasm, while process-driven, must accommodate abstract thought to effectively translate concepts into executable forms.

For instance, Phas’s metaphorical “Forest of Thought” relies on concrete executable branches to maintain coherence, and Phasm’s macros often encapsulate abstract reasoning into actionable symbols. This interplay highlights how metaphor and metonymy are not distinct silos but overlapping strategies in cognition and design.

The concept of learning in Phas/Phasm is high-entropy data (ideas, uncertainty, exploration) into low-entropy data (knowledge, structure). Phas is Exploration or search space (Metaphor) and Phasm is Categorisation and structure (Metonymy).

There is inevitable loss when distilling trees or branches into macros especially in a non-deterministic setting but efficiencies can be made in conversion.

Phas and Phasm

A widescreen conceptual illustration of two abstract frameworks: Phas and Phasm. On the left side, ‘Phas’ is represented as a glowing, intricate forest with dynamic, interconnected trees symbolizing exploration, ideas, and high-entropy data. The forest is vibrant and chaotic, full of energy. On the right side, ‘Phasm’ is depicted as a precise geometric crystalline grid, symbolizing categorization, knowledge, and low-entropy data. A gradient bridge connects the two, transitioning smoothly from the organic complexity of the forest to the structured clarity of the crystalline grid. The scene is illuminated by a soft ethereal glow, emphasizing the contrast between chaos and order, exploration and structure.