<div dir="auto">Hi Andreas, I am considering X3DJSAIL and X3DJSONLD code generators and how they could generate code more amenable to revision control. Some use incremental integers to create unique variable names and others create hierarchies susceptible to rapid revision when modified using LLMs. It seems like we need specific tools for this rather than line by line diffing.</div><div dir="auto"><br></div><div dir="auto">That said, xmldiff and jsondiff do a pretty good job, except on JavaScript. Now that numbers are being rounded in SAI, that’s good too.</div><div dir="auto"><br></div><div dir="auto">Ideally, one would rely on XML being what changed, and you accurately state x3dom. But with HAnim, that might be too many tokens, and run up a lot of money. My hope is for non-mesh equations with parameters to generate humanoids. I saw something mentioned on that recently, so I’m coming back to that. If only 5% of DNA is used, are we getting in the LLM ballpark?</div><div dir="auto"><br></div><div dir="auto">Ideally, indeed, something very high level, like English is desired, controlling an existing humanoid.</div><div dir="auto"><br></div><div dir="auto">I think you mention this: To translate a humanoid from .x3d to .glb, I don’t feed LLM humanoid.x3d and humanoid.glb, I tell it to convert basic x3d nodes to .glb, and produce python to do the conversion, which I feed back into LLM, enhancing the python. The LLM can look up X3D and glb (looking for python libraries) on its own.</div><div dir="auto"><br></div><div dir="auto">John</div><div dir="auto"><br><div class="gmail_quote gmail_quote_container" dir="auto"><div dir="ltr" class="gmail_attr">On Thu, Apr 30, 2026 at 8:09 AM Andreas Plesch via x3d-public <<a href="mailto:x3d-public@web3d.org">x3d-public@web3d.org</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-style:solid;padding-left:1ex;border-left-color:rgb(204,204,204)"><div dir="auto"><div dir="ltr"><div class="gmail_quote"><div>Hi Len,</div><div><br></div><div>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.</div><div><br></div><div>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 ?</div><div dir="auto"><br></div><div dir="auto">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.</div><div dir="auto"><br></div><div dir="auto">Andreas</div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-style:solid;padding-left:1ex;border-left-color:rgb(204,204,204)">Date: Tue, 28 Apr 2026 14:25:27 -0500<br>
From: <a href="mailto:cbullard@hiwaay.net" rel="noreferrer" target="_blank">cbullard@hiwaay.net</a><br>
To: X3D AI Working Group <<a href="mailto:ai@web3d.org" rel="noreferrer" target="_blank">ai@web3d.org</a>>, <a href="mailto:x3d-public@web3d.org" rel="noreferrer" target="_blank">x3d-public@web3d.org</a><br>
Subject: [x3d-public] MCCF Implementation Specification V3<br>
Message-ID: <<a href="mailto:147eb1b15cc3b2e324ae241a76bcc11e@hiwaay.net" rel="noreferrer" target="_blank">147eb1b15cc3b2e324ae241a76bcc11e@hiwaay.net</a>><br>
Content-Type: text/plain; charset=US-ASCII; format=flowed<br>
<br>
Good afternoon:<br>
<br>
This is the github link for the Multi Channel Coherence Field (MCCF) <br>
version 3 implementation. This was created after review of the draft <br>
by all participating members (Claude, ChatGPT, Grok, Gemini and Len <br>
Bullard). Work on implementation begins tomorrow.<br>
<br>
Comments or suggestions are welcome but we are not adding additional <br>
requirements. This version is where the relationship to the X3D standard <br>
and implementations gets tighter. I am will ask questions in this forum <br>
to help clarify this. We are currently running the X_Lite viewer and <br>
sanity testing on the X_Lite editor. I am happy to include other <br>
viewers as possible. The XML design is clean for exporting and <br>
implementing scenes. I am happy to provide any instance of these to <br>
interested parties. We will start keeping those in the GitHub.<br>
<br>
I note that one member of this community has forked the repo. Thank you <br>
for your interest. Your contributions are welcome. We are going fast <br>
so refresh as you need. A goal of the project is to keep as much <br>
content contexts (application domains) as external as possible to ensure <br>
the general applicability of the MCCF to different applications. Some <br>
of the original narrative basis has leaked into the design but we will <br>
clear that out.<br>
<br>
Thanks,<br>
<br>
len<br>
<br>
<a href="https://github.com/artistinprocess/mccf/blob/master/MCCF_V3_SPEC.md" rel="noreferrer noreferrer" target="_blank">https://github.com/artistinprocess/mccf/blob/master/MCCF_V3_SPEC.md</a><br></blockquote></div><br></div>
<br><br><div data-smartmail="gmail_signature"><div dir="ltr"><div>Andreas Plesch<br>Waltham, MA 02453</div></div></div></div>
_______________________________________________<br>
x3d-public mailing list<br>
<a href="mailto:x3d-public@web3d.org" target="_blank">x3d-public@web3d.org</a><br>
<a href="http://web3d.org/mailman/listinfo/x3d-public_web3d.org" rel="noreferrer" target="_blank">http://web3d.org/mailman/listinfo/x3d-public_web3d.org</a><br>
</blockquote></div></div>