[x3d-public] MCCF V3 Implementation

[cbullard at hiwaay.net]

Hello Andreas:

I very much appreciate that you have taken and interest.  V3 is a big 
move and will take some time.  V1 and V2 were about getting the emote 
engine to work and threshing out the concepts of apply semantic collapse 
and energy models (why we call it Q personna) to the dynamic creation of 
meaning, a fancy way of saying a narrative generator.  I am throwing 
things against the wall to see what sticks. :)

So we aren't sure what will work best in the interface at this time.  
The new scene composer will allow us to export a basic scene as 
described here which an X3D artist can then add to as they like.  I do 
want to keep the MCCF and X3D layers as separate as possible for clean 
layering but there is a lot to learn about the new X3D features and the 
best way to implement that.  V3 is the sandbox for that work.

There is a set of cultivars for agent initialization that now load from 
the XML instance.  And one can add more.  I avoid JSON as much as 
possible because it lacks the hierarchies that LLMs like.  But JSON 
where prudent.

In V4 I will look at using the system to produce training data for the 
LLM.  A foundation model can't be trained but it can produce data for 
training the local LLMs. So a sandbox is required in case the LLM 
becomes unstable.  If this works, the local LLM learns the character 
just as an actor does and different LLMs can learn the same part.  While 
I think of this in theatre terms. it should be applicable to other 
domains.  I prefer after a long career of working for the MIC to stay in 
art.

The attached image is the Scene Composer for V3.  MCCF Scene Composer - 
Zones, Waypoints, Paths with Emotional Energy and Character Arcs.  
Emotional States of Character Evolve as they move down a path toward a 
waypoint creating a dynamic emotional state.  A zone is a location which 
has a fixed emotional pressure on the character that attracts them so is 
functionally a character in a fixed location.  The zones and characters 
are semantic attractors.  A scene in rendered in X3D as basic 3D 
geometric shapes in precise locations which are exported then replaced 
by 3D artists with richer X3D geometry such as H-anim avatars, scenery, 
buildings, etc.  Sound nodes can be activated or zone themes can be 
assigned per zone affect types.

Thanks for forking the project.  It is a hopeful event.  :)  BTW, my 
daughter works at Harvard as an assistant library curator.

len

On 2026-04-30 7:59 am, Andreas Plesch via x3d-public wrote:
> Hi Len,
> 
> I forked the repo as the easiest way to just take a quick look and try
> some things. My main interest was to see how the X3D interface works
> and how x3dom might be a good match. I think it could be that by using
> more direct DOM manipulation of the X3D scene which could be simpler
> and more 'understandable' to the LLMs generating the code. This would
> also mean moving logic out of x3d scripts and into an external bridge
> layer. Please proceed at full speed since I do not anticipate being
> able to contribute to the core MCCF idea and implementation.
> 
> I noticed there is a non-LLM agent to choose from when running an arc.
> This could be useful for development purposes. Is there an expected
> impact on the x3d visualization doing so ?
> 
> It may be nice to have the coding assistants generate more fine
> grained commits and PRs with explanations for human consumption,
> perhaps when things settle down.
> 
> Andreas
> 
>> Date: Tue, 28 Apr 2026 14:25:27 -0500
>> From: cbullard at hiwaay.net
>> To: X3D AI Working Group <ai at web3d.org>, x3d-public at web3d.org
>> Subject: [x3d-public] MCCF Implementation Specification V3
>> Message-ID: <147eb1b15cc3b2e324ae241a76bcc11e at hiwaay.net>
>> Content-Type: text/plain; charset=US-ASCII; format=flowed
>> 
>> Good afternoon:
>> 
>> This is the github link for the Multi Channel Coherence Field (MCCF)
>> 
>> version 3 implementation.   This was created after review of the
>> draft
>> by all participating members (Claude, ChatGPT, Grok, Gemini and Len
>> Bullard).  Work on implementation begins tomorrow.
>> 
>> Comments or suggestions are welcome but we are not adding additional
>> 
>> requirements. This version is where the relationship to the X3D
>> standard
>> and implementations gets tighter.  I am will ask questions in this
>> forum
>> to help clarify this.  We are currently running the X_Lite viewer
>> and
>> sanity testing on the X_Lite editor.  I am happy to include other
>> viewers as possible.   The XML design is clean for exporting and
>> implementing scenes.  I am happy to provide any instance of these to
>> 
>> interested parties.  We will start keeping those in the GitHub.
>> 
>> I note that one member of this community has forked the repo.  Thank
>> you
>> for your interest.  Your contributions are welcome.  We are going
>> fast
>> so refresh as you need.  A goal of the project is to keep as much
>> content contexts (application domains) as external as possible to
>> ensure
>> the general applicability of the MCCF to different applications.
>> Some
>> of the original narrative basis has leaked into the design but we
>> will
>> clear that out.
>> 
>> Thanks,
>> 
>> len
>> 
>> https://github.com/artistinprocess/mccf/blob/master/MCCF_V3_SPEC.md
> 
> Andreas Plesch
> Waltham, MA 02453
> _______________________________________________
> x3d-public mailing list
> x3d-public at web3d.org
> http://web3d.org/mailman/listinfo/x3d-public_web3d.org
-------------- next part --------------
A non-text attachment was scrubbed...
Name: MCCFSceneComposer.png
Type: image/png
Size: 324796 bytes
Desc: not available
URL: <http://web3d.org/pipermail/x3d-public_web3d.org/attachments/20260430/946b7b99/attachment-0001.png>