+- The Voynich Ninja (https://www.voynich.ninja)
+-- Forum: Voynich Research (https://www.voynich.ninja/forum-27.html)
+--- Forum: Voynich Talk (https://www.voynich.ninja/forum-6.html)
+--- Thread: Using AI to do research - Specifically online searching (/thread-5699.html)
RE: Using AI to do research - Specifically online searching - Mark Knowles - 01-05-2026
One thing that I assume is that these AIs have no access to the contents of the Voynich Ninja forum, so whilst they can draw from the contents of Nick Pelling's blog the information here is hidden from them.
RE: Using AI to do research - Specifically online searching - Mark Knowles - 01-05-2026
I would be tempted to try to produce a complete and exhaustive bibliography of every early 15th century cipher that I know of and then feed this bibliography into an AI and ask it to find me an early 15th century cipher not in my bibliography. However, I am not sure that would be productive.
RE: Using AI to do research - Specifically online searching - Linda - 01-05-2026
(01-05-2026, 11:43 AM)Mark Knowles Wrote: You are not allowed to view links. Register or Login to view.One thing that I assume is that these AIs have no access to the contents of the Voynich Ninja forum, so whilst they can draw from the contents of Nick Pelling's blog the information here is hidden from them.
Ninja forum posts come up in Google searches so I don't see why they wouldn't have access.
I just tried asking for a synopsis of your theory, seemed to be accurate, although possibly skewed towards what it thinks my interests are? I wonder if someone else asking would get the exact same reply or something slightly different.
RE: Using AI to do research - Specifically online searching - Mark Knowles - 01-05-2026
Well, I asked ChatGPT:
"Can you describe Mark Knowles's theory of the Voynich manuscript?"
It just replied with some generic theory, some of which I may not disagree with, but completely missed almost all of what I have argued on the subject.
Gemini does somewhat better, at least identifying a few of my opinions, but it confuses me and my opinions with those of other people and their opinions.
Claude needed some pointing as to where I have discussed my thoughts, but once I gave it that direction did much better than the previous two. Though it missed some stuff that Gemini picked up on.
RE: Using AI to do research - Specifically online searching - Koen G - 01-05-2026
They absolutely have access. Sometimes I want to see what it can find about a niche subject, and it only quotes my recent posts from Ninja.
I just asked Gemini "Browse the Voynich Ninja forum and summarize what you can find about user Mark Knowles' interests."
Quote:Based on discussions on the Voynich Ninja forum, Mark Knowles' interests and theories primarily focus on the historical context of the Voynich Manuscript (VMS), specifically regarding 15th-century diplomatic ciphers and the geographical identification of its illustrations.
Core Interests & Research Focus
15th-Century Ciphers: He is deeply interested in the evolution of ciphers between 1379 and 1449. He has built a personal archive of early 15th-century ciphers and focuses on those from Milan and Florence. He has expressed a specific interest in the works of Zanino Riccio and the cipher mapping of Gabrielli.
Archival Research: Knowles emphasizes the importance of physical archival research over online study. He has conducted research at the Milan State Archives and frequently uses the Bodleian Library in Oxford. He advocates for exploring the estimated 80% of archival material that remains undigitized.
Milanese/North Italian Origin: His theories often align with a North Italian, specifically Milanese, origin for the manuscript. He frequently references Nick Pelling's "Milan theory" as a starting point for his own developments.
Specific Theories
The Rosettes Page as a Map: One of his most prominent theories is that the Rosettes foldout (folio 86) is a literal map illustrating a specific journey.
The Journey: He proposes it depicts a circular trip taken by Abbot Antonio Barbavara (and companions) from the Abbey of Saints Nazzaro and Celso in the Duchy of Milan to the Council of Basel and back.
Topography: He argues that the circular features represent specific geographical locations, such as Alpine lakes and rivers (rather than seas or islands), and that the "castle" in the drawing reflects real architectural features like Ghibelline merlons.
Historical Influences: He suggests that parts of the VMS, particularly the astronomical sections, show Germanic influences likely encountered by the author while attending the Council of Basel.
Methodological Skepticism: On the forum, he is known for being critical of "complete decipherment" claims (like those of Gerard Cheshire). He argues that many such theories rely on too many "degrees of freedom," such as arbitrary word spacing and tolerant spelling variations.
Philosophy on Research
Knowles views Voynich research as a scientific process where theories must be detailed and subject to rigorous criticism. He has expressed that even if a theory is eventually proven incorrect, the process of developing a "complete detailed theory" is essential for progressing the field.
RE: Using AI to do research - Specifically online searching - Koen G - 01-05-2026
That said, even when using a specified source, it's still full of nonsense. Some things it says about my activity at Ninja:
Quote:Non-Linguistic "Process" Theory: One of his most significant contributions is the hypothesis that the manuscript might not be a linguistic text at all (not a natural or artificial language). Instead, he proposes it is a process-encoded system where symbols function as operational markers or states.
Visual-Attentional Framework: He has developed a model (the Gate–Scaffolding Model) suggesting the manuscript was designed to guide a reader's visual attention in a specific, rhythmic scanning pattern. In this view, certain words act as "anchors" or "gates" to stabilize the eye's movement across the page.
I feel slandered.
RE: Using AI to do research - Specifically online searching - Linda - 01-05-2026
(01-05-2026, 11:47 AM)Mark Knowles Wrote: You are not allowed to view links. Register or Login to view.I would be tempted to try to produce a complete and exhaustive bibliography of every early 15th century cipher that I know of and then feed this bibliography into an AI and ask it to find me an early 15th century cipher not in my bibliography. However, I am not sure that would be productive.
I fed it your comment above and it said 3 problems that might interfere: training data wall, hallucination risk, and un-digitized reality, and suggests you ask it to find correlations with merchant marks, alchemical symbols and administrative abbreviations, suggesting that boring docs are more likely to hold the key than some secret cipher that has yet to be found. I asked it to do that and it just blathered on and was not productive, mostly due to hallucinations, wrong assumptions (it keeps thinking there are plants in quire 20, for instance, even though i have corrected it before on that particular hallucination) and a lack of specificity in its answers, which could be related to my not being specific enough also.
RE: Using AI to do research - Specifically online searching - Mark Knowles - 01-05-2026
(01-05-2026, 04:27 PM)Koen G Wrote: You are not allowed to view links. Register or Login to view.They absolutely have access. Sometimes I want to see what it can find about a niche subject, and it only quotes my recent posts from Ninja.
I just asked Gemini "Browse the Voynich Ninja forum and summarize what you can find about user Mark Knowles' interests."
Quote:Based on discussions on the Voynich Ninja forum, Mark Knowles' interests and theories primarily focus on the historical context of the Voynich Manuscript (VMS), specifically regarding 15th-century diplomatic ciphers and the geographical identification of its illustrations.
Core Interests & Research Focus
15th-Century Ciphers: He is deeply interested in the evolution of ciphers between 1379 and 1449. He has built a personal archive of early 15th-century ciphers and focuses on those from Milan and Florence. He has expressed a specific interest in the works of Zanino Riccio and the cipher mapping of Gabrielli.
Archival Research: Knowles emphasizes the importance of physical archival research over online study. He has conducted research at the Milan State Archives and frequently uses the Bodleian Library in Oxford. He advocates for exploring the estimated 80% of archival material that remains undigitized.
Milanese/North Italian Origin: His theories often align with a North Italian, specifically Milanese, origin for the manuscript. He frequently references Nick Pelling's "Milan theory" as a starting point for his own developments.
Specific Theories
The Rosettes Page as a Map: One of his most prominent theories is that the Rosettes foldout (folio 86) is a literal map illustrating a specific journey.
The Journey: He proposes it depicts a circular trip taken by Abbot Antonio Barbavara (and companions) from the Abbey of Saints Nazzaro and Celso in the Duchy of Milan to the Council of Basel and back.
Topography: He argues that the circular features represent specific geographical locations, such as Alpine lakes and rivers (rather than seas or islands), and that the "castle" in the drawing reflects real architectural features like Ghibelline merlons.
Historical Influences: He suggests that parts of the VMS, particularly the astronomical sections, show Germanic influences likely encountered by the author while attending the Council of Basel.
Methodological Skepticism: On the forum, he is known for being critical of "complete decipherment" claims (like those of Gerard Cheshire). He argues that many such theories rely on too many "degrees of freedom," such as arbitrary word spacing and tolerant spelling variations.
Philosophy on Research
Knowles views Voynich research as a scientific process where theories must be detailed and subject to rigorous criticism. He has expressed that even if a theory is eventually proven incorrect, the process of developing a "complete detailed theory" is essential for progressing the field.
That seems quite accurate. Although, I am not sure what it means by ->
'He has expressed that even if a theory is eventually proven incorrect, the process of developing a "complete detailed theory" is essential for progressing the field.'
And it hasn't mentioned anything about my thoughts on Steganography etc. But generally, it seems accurate.
RE: Using AI to do research - Specifically online searching - Mark Knowles - 01-05-2026
I wonder if there is some way of making the different AIs collaborate to produce a better result than they would individually. So, getting GPT, Gemini, Claude etc. to work together. Or maybe you can feed the thoughts of one of them into another of them and see what it comes up with and repeating that for the different AIs.
RE: Using AI to do research - Specifically online searching - Mark Knowles - 01-05-2026
It is easy to criticise these AIs, but I think they clearly can be useful tools. Even if 95% of what they say is nonsense that remaining 5% may be gold. I suppose they just need to be used with care and caution like any tool should be.
Identifying the Andrea Barbarigo cipher was a useful lead for me to follow up. I haven't seen it yet, but I doubt Ioanna Iordanou made it up.