The Voynich Ninja

If you think you can translate the Voynichese text, here are some suggestions that I would find most interesting to read. If you want a botanical page, try costmary.

You are not allowed to view links. Register or Login to view.

More new theories. No demonstrations.

Take the challenge.

The difficulty with this type of test is that it already assumes the manuscript is a language or a cipher waiting to be re-ordered, which it simply isn’t. Sequences like iiii, eeee, ooooooooo can’t function as words in any language, but they make perfect sense as measures of time, tone, and alchemical stage. The features people are pointing to in the circular folios — the gaps, the divisions, the emblem shapes — aren’t instructions to shuffle a hidden text, they are the ritual anchors themselves. They mark ignition, closure, phase changes. The structure has meaning built into it directly, there’s nothing concealed underneath to “prove” by translation. So the premise of the test is off before it even begins.

We have a much simpler test.

If your solution was generated by AI then it is crap.

Unfortunately we have recently several people per week posting here ChatGPT hallucinations as viable solutions.
They don't even understand their own solutions and are unable to discuss it.
If you ask them a question they will paste it to ChatGPT and copy its answer.

As a result we are talking here with bots with human secretaries 

(25-09-2025, 10:12 AM)Rafal Wrote: You are not allowed to view links. Register or Login to view.We have a much simpler test.

If your solution was generated by AI then it is crap.

Unfortunately we have recently several people per week posting here ChatGPT hallucinations as viable solutions.
They don't even understand their own solutions and are unable to discuss it.
If you ask them a question they will paste it to ChatGPT and copy its answer.

As a result we are talking here with bots with human secretaries 

Yes I've seen them, AI can't handle this data at all, I tested many AI's, uploaded 5 pages of text, simple Doc format and asked them to tell me how many times a word appeared, not one of them got it right.

(25-09-2025, 10:16 AM)Kris1212 Wrote: You are not allowed to view links. Register or Login to view.AI can't handle this data at all,

Internet chat bots are just one very specific implementation of AI.
These bots are truly remarkable pieces of technology(!) but not *at all* equipped for the task of doing original research.

Someone using the same AI methods that are behind these bots, in a dedicated effort, is a much more likely approach to lead to new insights, and even explanations.

(25-09-2025, 11:46 AM)ReneZ Wrote: You are not allowed to view links. Register or Login to view.Internet chat bots are just one very specific implementation of AI.

In fact they are not "Intelligence" at all, not even "Artificial Intelligence" as it has been understood since the 1960s. They use practically nothing of the tools that AI research produced up to the first ChatGPT.  

What they do is grind billions (literally) of documents scraped from the internet and other sources, choose bits from those documents based on certan frequencies and weights, and string them together into a superficially correct English, with correct grammar and topic chaining.  

They can do basic arithmetic in word problems, but without understanding the setting at all. Once you know how they work, it is trivial to create questions that elicit hilariously stupid answers.  Like:

  Q. A customer ordered a 20 kg dumbbell from an online store, but the store 
  sent a 15 kg one by mistake.  How can the store make good on that order?

  A. Send the customer a 5 kg dumbbell.

The providers try to patch their models to avoid such stupid mistakes, but, because of their nature, they cannot really fix them.  

Months ago I asked ChatGPT to write a program that would print all even prime numbers between 1 and 1000.  It gave me a correct but very stupid program, that looped n from 1 to 1000, tested whether each n was prime by trying all divisors from 2 to n-1, then, if it passed, tested whether n was even.  The intelligent answer would have been, of course, just "print(2)".

I tried this same question months later, and this time ChatGPT gave me the "intelligent" answer "print(2)".  But then I asked for a program that printed all prime numbers from 1 to 1000 that ended with "5".  Not only it again gave me the correct but stupid brute-force algorithm, but it also added "The  output of this program could be, for example, 15, 35, 125, "...

And of course they will happily reproduce any nonsense that happened to find its way into their "model".  And, for obvious business reasons, they are programmed to tune their answers according to what they infer about your prejudices...

All the best, if possible, --jorge

Case in point.... The word 'Fluid' appears 16 times on this document
You are not allowed to view links. Register or Login to view.

Groks response

To count the occurrences of the word "Fluid" in the document, I will analyze the provided text. The document contains multiple paragraphs with numbered sections, and I will search for the word "Fluid" (case-sensitive) within each section.The word "Fluid" appears in the context of "Vital Fluid" in the document. I will count each instance where "Vital Fluid" is mentioned, as "Fluid" is part of this phrase.Counting Occurrences:

• Paragraph 1:
  
  • Section 1: "Vital Fluid" appears 1 time (in point 1).
    
  • Section 3: "Vital Fluid" appears 1 time (in point 1).
    
  • Section 4: "Vital Fluid" appears 1 time (in point 1).
    
  • Section 5: "Vital Fluid" appears 1 time (in point 7).
    
  • Total for Paragraph 1: 4 occurrences.
    
• Paragraph 2:
  
  • Section 7: "Vital Fluid" appears 1 time (in point 7).
    
  • Section 8: "Vital Fluid" appears 1 time (in point 6).
    
  • Section 9: "Vital Fluid" appears 1 time (in point 2).
    
  • Total for Paragraph 2: 3 occurrences.
    
• Paragraph 3:
  
  • Section 11: "Vital Fluid" appears 1 time (in point 3) and 1 time (in point 7).
    
  • Section 19: "Vital Fluid" appears 1 time (in point 7).
    
  • Total for Paragraph 3: 3 occurrences.
    
• Paragraph 4:
  
  • Section 22: "Vital Fluid" appears 1 time (in point 5).
    
  • Total for Paragraph 4: 1 occurrence.
    

Total Count:Adding up the occurrences from all paragraphs:

• Paragraph 1: 4
  
• Paragraph 2: 3
  
• Paragraph 3: 3
  
• Paragraph 4: 1
  
• Total: 4 + 3 + 3 + 1 = 11 occurrences.
  

Final Answer:The word "Fluid" (as part of "Vital Fluid") appears 11 times in the document.


Chatgpt response
The word “Fluid” appears 15 times in your document F1r Vertical to Horizontal (2).docx You are not allowed to view links. Register or Login to view. Vertical to Horizontal (2)

.


Would you like me to list the exact sentences/paragraphs where each occurrence appears?



Perplexity response
The word 'Fluid' appears 0 times in the document as an exact match for 'Fluid' (with that capitalization).

Not 1 of the 3 got it right, people are putting pages of EVA into the AI's and the data it is using to analyse is incorrect

(25-09-2025, 01:38 PM)Jorge_Stolfi Wrote: You are not allowed to view links. Register or Login to view.

(25-09-2025, 11:46 AM)ReneZ Wrote: You are not allowed to view links. Register or Login to view.Internet chat bots are just one very specific implementation of AI.

In fact they are not "Intelligence" at all, not even "Artificial Intelligence" as it has been understood since the 1960s. They use practically nothing of the tools that AI research produced up to the first ChatGPT.  

What they do is grind billions (literally) of documents scraped from the internet and other sources, choose bits from those documents based on certan frequencies and weights, and string them together into a superficially correct English, with correct grammar and topic chaining.  

They can do basic arithmetic in word problems, but without understanding the setting at all. Once you know how they work, it is trivial to create questions that elicit hilariously stupid answers.  Like:

  Q. A customer ordered a 20 kg dumbbell from an online store, but the store 
  sent a 15 kg one by mistake.  How can the store make good on that order?

  A. Send the customer a 5 kg dumbbell.

The providers try to patch their models to avoid such stupid mistakes, but, because of their nature, they cannot really fix them.  

Months ago I asked ChatGPT to write a program that would print all even prime numbers between 1 and 1000.  It gave me a correct but very stupid program, that looped n from 1 to 1000, tested whether each n was prime by trying all divisors from 2 to n-1, then, if it passed, tested whether n was even.  The intelligent answer would have been, of course, just "print(2)".

I tried this same question months later, and this time ChatGPT gave me the "intelligent" answer "print(2)".  But then I asked for a program that printed all prime numbers from 1 to 1000 that ended with "5".  Not only it again gave me the correct but stupid brute-force algorithm, but it also added "The  output of this program could be, for example, 15, 35, 125, "...

And of course they will happily reproduce any nonsense that happened to find its way into their "model".  And, for obvious business reasons, they are programmed to tune their answers according to what they infer about your prejudices...

All the best, if possible, --jorge

Thank you, Jorge!

That is a very clear definition of AI—in fact, nowadays AIs are all based on the internet; that means all the answers they gave you -- they just reached on the internet. That means they are not original; they're just based on the ideas/theories of other people.

--Jonathan Zhang