Darrell Huff’s (1954) “How to Lie With Statistics” is a twentieth century classic that’s well worth reading (I have a well-thumbed copy on my bookshelf that I bought back in the 1980s). It’s basically a breezy introduction to statistics, that concentrates largely on how people get things wrong in order to get across the general idea of how you might (possibly, hopefully) try to get things right in your own work.

A journalist rather than an academic statistician, Huff’s book ended up selling more than 1.5 million copies. You can hear echoes of his reversed-expectations presentation in numerous other book titles, such as Bill Hartston’s “How to Cheat at Chess”.

Sadly, The Truth Is Much, Much Worse

When later I did statistics modules at University, the awful truth slowly dawned on me: even though tools (such as Excel) make it easy to perform statistical procedures, stats really isn’t just a matter of “running the numbers”, cranking out an answer, and drawing some persuasive-looking graphs.

Even just conceiving a statistical experiment (e.g. something that’s based on good data, and that stands a chance of yielding meaningful results) is extraordinarily hard. Designing statistical experiments (e.g. understanding the sampling biases that are inevitably embedded in the data, and then working out how to work around them) is also hugely tricky. Executing them is no mean feat either: and then – finallyinterpreting them is fraught with difficulty.

In general, my own experience of statistical experiments is that at least half are fatally misconceived; of the remainder, half are horribly misdesigned; of the remainder of that, at least half are sadly misexecuted; and of the remainder of that, at last half of the results are tragically misinterpreted. Note that the overall success rate (<5%) is for people who broadly know what they’re doing, never mind idiots playing with Excel.

A Story About Stats

Back when I was doing my MBA, one of the final marked pieces was for the statistics module. When I took a look at the data, it quickly became clear that while most of the columns were real, one in particular had been faked up. And so I wrote up my answer saying – in a meta kind of way – that because that (fake) column was basically synthetic, you couldn’t draw reliable conclusions from it. And so the best you could do in practice was to draw conclusions from the other non-synthetic columns.

I failed the module.

So, I made an appointment with the lecturer who marked it, who also happened to be the Dean of the Business School.

  • I said: Why did you fail this piece?
  • He said: Because you didn’t get the right answer.
  • I said: But the column for the ‘right’ answer is fake.
  • He said: I don’t think so.
  • I said: Well, look at this [and showed him exactly how it had been faked]
  • He said: Oh… OK. I didn’t know that. But… it doesn’t matter.
  • I said: errrm… sorry?
  • He said: you’ve got a Distinction anyway, so there’s no point me changing this mark

And so I still failed the statistics module.

The Voynich Manuscript and Stats

If you think Voynich Manuscript researchers who run statistical tests on Voynichese are somehow immune to these fundamental hazards, I don’t really think you’re paying enough attention.

Until you accept that the core problems inherent in Voynichese transcriptions – there are many, and they run deep – will inevitably permeate all your analyses, you really are just running the numbers for fun.

The main things that bother me (though doubtless there are others that I can’t think of right now):

  • Transcription assumptions
  • Transcription error rates
  • Running tests on the whole Voynich Manuscript, rather than on sections (e.g. Q13, Q20, Herbal-A)
  • How Voynichese should be parsed into tokens (this has bugged me for 20 years!)
  • Copying errors and Voynichese “weirdoes”
  • The bifolios being out of order
  • Whether there is a uniform ‘system’ underlying both Currier A and Currier B
  • The problems with top-line text
  • The problems with line-initial letters
  • The problems with line-final letters
  • etc

With so many parallel things to consider, I honestly think it should be no surprise that most attempts at Voynich analysis fail to achieve anything of value.

Voynich Theories

I have no doubt that researchers do their best to be rational and sensible, but many Voynich theories – or, perhaps more accurately, Voynich ‘approaches’ – are built upon a fundamentally flawed statistical ‘take’, e.g. that Voynichese is just a simple (but highly obscure) text.

Unpopularly, this seems to be true of just about all ‘Baxian’ Voynich linguistic analyses. Statistically, nothing supports the basic assumption of a ‘flat’ (but obscure) language. In fact, Voynichese is full of confounding, arbitrary, difficult, unlanguagelike behaviours (see the incomplete list above), all of which you have to compensate for to get your data to a point where you even begin to have something remotely language-like to work with. But hardly anybody ever does that, because it’s too tricky, and they’re not genuinely invested enough to do the ‘hard yards’.

It’s also true of Gordon Rugg’s table ‘take’; and of just about all simple ciphers; and – also unpopularly – of hoax theories (why should meaningless text be so confounded?) And so forth.

The sad reality is that most researchers seem to approach Voynichese with a pre-existing emotional answer in mind, which they then true to justify using imperfect statistical experiments. More broadly, this is how a lot of flawed statistical studies also work, particularly in economics.

In fact, statistics has become a tool that a lot of people use to try to support the lies they tell themselves, as well as the lies their paymasters want to be told. This is every bit as true of Big Oil and alt.right politics as of Voynichology. Perhaps it’s time for an even more ironic 21st century update to Darrell Huff’s book – “How To Lie To Yourself With Statistics”?

Like most people, I’ve read numerous articles about ChatGPT recently. Perhaps the most entertaining was where ChatGPT (sort of) played chess against the #1 chess engine Stockfish, with hilarious consequences (if you’re a chess player, that is).

However, few articles manage to get the point across that ChatGPT is not an all-knowing Oracle, but rather something that is trying to please you by providing answers that are as realistic-looking as it can make them (rather than actually realistic). It’s entertainment, people (and definitely not real).

Perhaps if I gave some examples you’ll see what I’m talking about…

“Did Filarete have his own herbal manuscript?”

I asked ChatGPT this question, because it was something which I already knew the answer to (and had blogged about back in 2008, and also since). The right answer is that Filarete did have his own herbal manuscript (it was mentioned in fol.78r of MS Ashburnham 198, “Sed et Antonius Averlinus Philaretus lingua vernacula scripsit eleganter“), but as far as I know, nobody knows if it or a copy of it still exists.

ChatGPT started safely and correctly:

There is no known herbal manuscript that can be definitively attributed to Filarete, the fifteenth-century Italian architect and writer. Filarete is best known for his architectural treatise, the “Treatise on Architecture,” which he wrote in the early 1460s.

ChatGPT

However, our chatty digital friend then went a bit off-piste:

However, there are some herbal manuscripts from the same general period that are associated with Filarete or have been attributed to him. For example, there is a manuscript in the Bibliotheca Augusta in Wolfenbüttel, Germany, that is sometimes referred to as the “Herbal of Filarete.” This manuscript contains descriptions and illustrations of various plants and their medicinal uses, but it is not clear whether Filarete was actually the author of the manuscript or was simply associated with it in some way.

ChatGPT

Interesting, I thought, even if I didn’t believe a word of it. It went on:

There are also other herbal manuscripts from the fifteenth century that are similar in style and content to the “Herbal of Filarete” and may have been produced by the same workshop or circle of artists and writers. These manuscripts are sometimes referred to as the “Herbarium of Apuleius” or the “Herbarium of Pseudo-Apuleius” and contain similar descriptions and illustrations of plants and their uses.

ChatGPT

“What is the shelfmark of that “Herbal of Filarete” you mentioned?”

I still didn’t believe a word, so asked it: “What is the shelfmark of that “Herbal of Filarete” you mentioned?” The response I got back was a little unexpected:

I apologize for the confusion in my previous response. Upon further research, I could not find any evidence of a manuscript called the “Herbal of Filarete” in the Bibliotheca Augusta in Wolfenbüttel, Germany.

I believe there may have been a misunderstanding or confusion with other sources. While there are many herbal manuscripts from the medieval period, there is no known herbal manuscript that can be definitively attributed to Filarete.

I apologize for any confusion or misinformation my previous response may have caused. If you have any further questions, please feel free to ask.

ChatGPT

It’s certainly true that the Bibliotheca Augusta in Wolfenbüttel has at least one Pseudo-Apuleius manuscript, so it looked like there was just some confusion going on. Gigantic input dataset aside, ChatGPT really isn’t anything like Google, so it would be grossly unfair to imagine that it is doing anything like the same thing when it tries to answer a query.

So I decided to take a different tack, to see if I could flush anything out about what was going on.

“Are there any herbal manuscripts associated with Filarete?”

Maybe there’s a herbal manuscript out there that’s loosely associated with Filarete or his coterie that I don’t know about, I thought. So I tried to poke the bear again (but in a slightly gentler way than before).

Can you guess how ChatGPT responded? I think you can. As before, the first paragraph was fairly solid:

To my knowledge, there are no herbal manuscripts that can be definitively attributed to Filarete, the fifteenth-century Italian architect and writer. Filarete is best known for his architectural treatise, the “Treatise on Architecture,” which he wrote in the early 1460s.

ChatGPT

But you might find the next paragraph eerily familiar:

While Filarete is not known to have authored any herbal manuscripts, there are some medieval manuscripts that contain descriptions and illustrations of plants and their medicinal uses that have been associated with him or with his circle of artists and writers. One example is a manuscript in the Biblioteca Medicea Laurenziana in Florence, Italy, that is sometimes referred to as the “Herbarium of Filarete.” This manuscript contains descriptions and illustrations of various plants and their medicinal uses, but it is not clear whether Filarete was actually the author of the manuscript or was simply associated with it in some way.

ChatGPT

Once again, this seems like an historical hallucination on ChatGPT’s part. The odd part is that it reprised the exact shape of its previous hallucinatory answer, but referring to a different top-end library. So, I again asked for the shelfmark of this imaginary manuscript…

“What is the shelfmark of that manuscript in Florence?”

That’s what I asked: and, sadly, you already know what ChatGPT’s reply is going to look like, because it’s basically the same as before:

I apologize for the error in my previous response. After further research, I have found that there is no known “Herbarium of Filarete” manuscript in the Biblioteca Medicea Laurenziana in Florence, Italy.

While Filarete is not known to have authored any herbal manuscripts, there are some medieval manuscripts that contain descriptions and illustrations of plants and their medicinal uses that have been associated with him or with his circle of artists and writers. One example is a manuscript known as the “Herbarium of Apuleius,” which is sometimes referred to as the “Herbal of Pseudo-Apuleius.” This manuscript is kept at the Bibliotheca Augusta in Wolfenbüttel, Germany, and has the shelfmark Codex Guelf. 82.7 Aug. 2°.

ChatGPT

What to make of this?

ChatGPT is undoubtedly a brilliant technical achievement. But as far as I can see, for now it’s just part of the entertainment industry.

Here, I do wonder whether the format of the question I asked kind of loosely defined the format of the answer ChatGPT inferred I was hoping to receive back: and that it then hallucinated enough additional stuff to complete the gaps in the answer format to provide a well-formed-looking answer. So maybe the whole point of ChatGPT is that the shape of the question defines the shape of the answer, even if there aren’t any actual facts inside the answer. Something to think about, anyway!

“So, how can I help you today,” smiled Dr Wayfit breezily but briefly, “Mr., uh, Smedley?”

“I’ve been struggling in lockdown”, the man replied, looking evasively through the third floor window of the medical centre. “My mental health is suffering. I’m feeling very anxious about… the vaccines. You know.”

“For something that does so much good, there are far too many conflicting messages out there”, the doctor said. “Do you… ” – she paused, looking him squarely in the eyes – “…rely on social media for information?”

“Oh no”, the man said, his face suddenly brightening, “I get my information direct. From the source.”

The doctor’s eyes narrowed quizzically. “You mean, from epidemiologists?”

“No!” Smedley laughed raucously, his head tipping backwards. “From the Voynich Manuscript. Everything about the coronavirus is in there, everything. Look at this.” He pulled out a crumpled piece of paper from an inside pocket and held it up for the doctor to see. “f69v. Proof. 100%. You can’t deny it. Even back in the 15th century, they knew. They Knew!

Dr Wayfit shook her head. “I’m sorry to have to tell you, but it’s actually a well-known fact that Wilfrid Voynich hoaxed the manuscript himself. You don’t have to look far to find well-illustrated websites arguing this point in a highly persuasive way.”

Shocked, Smedley leapt backwards towards the door, his picture of f69v clutched to his face in horror. “But… that makes no sense at all? What kind of crazy drugs are you self-administering?”

“No, it’s all just common sense”, she cooed reassuringly. “Take your f69v, for example – it’s nothing more complex than a series of brightly-coloured pipes arranged around a starfish, the same as literally millions of medieval diagrams.”

“Really? Is there even one medieval diagram remotely like it?”

She rolled her eyes extravagantly. “To be precise, it’s the same as literally millions of medieval diagrams could have been, had the person drawing it chosen to draw it that way. And so what Wilfrid Voynich was hoaxing was how any one of those million medieval diagrams could have looked, had the person drawing it chosen to draw it as a set of brightly-coloured pipes around a starfish.”

“An eight-armed starfish?”

“It’s a work of imagination, obviously.”

“But… it’s so obviously coronavirus”, Smedley spluttered, now purple in the face. “And even though I’ll happily admit that my conclusion can be difficult for some to accept, your explanation is ten times crazier. Maybe even a hundred times.”

“Look, there’s really no reason for you to feel so upset by the Voynich Manuscript. You’ve been in ‘qokdown’ for far too long, and we in VAnon are desperately keen for people to understand that…”

~ ~ ~ ~ ~ ~ ~ ~ ~

“So, Dr Wayfit”, the police detective asked, looking at the body crumpled on the pavement far below the medical centre’s smashed window, the picture of f69v grasped firmly in the dead man’s hands, “you must admit this is a bit of a strange tableau, right?”

“Not really”, she replied, her eyes darting around distractedly. “The moment poor Mr Smedley told me that he thought the Voynich Manuscript had meaningful content, I knew instantly he was quite deranged. Honestly, he was a clear danger to himself, and I don’t think there’s anything I could have done to prevent this awful tragedy.”

You might be interested to know that an interview with (relatively new) Voynich researcher Domingo Delgado was posted to YouTube a few days ago. In this, Delgado describes how he thinks the Voynich Manuscript was:

  • made in Italy (because he thinks the handwriting is distinctively Italian);
  • made in the 15th century (largely because of the same ‘4o’ pattern I went on about in The Curse of the Voynich back in 2006);
  • written in Latin (because that’s what educated Italians used back then); and
  • enciphered using a combination of substitution and “permutation” (I’m pretty sure he means ‘transposition’) tricks (though he doesn’t want to give any details away just yet, his book – to be published next year – will teach everyone how to decrypt Voynichese for themselves)

Having previously (in 2019) concluded that the Voynich’s author was Leon Battista Alberti, Delgado now thinks for 100% sure that it was funded by Federico da Montefeltro (though he doesn’t have any more detail than this).

He doesn’t yet know the author’s name, because the text’s combination of substitution and transposition means that it’s taking him a while to decrypt its text: so far, he has only managed to decrypt a few lines at a time.

Delgado also seems a bit cross that existing Voynich Manuscript researchers don’t seem to have taken his work seriously – in other words, that he hasn’t been given the seat at the top table he so rightly deserves.

(Hot tip: there is no top table – we all sit on the floor.)

f6r = Groundsel?

His decryption process seems largely to have been to look at the top two lines of herbal pages to see if they contain a tell-tale Latin plant-name that has been manipulated in some way. His key example seems to be f6r, which he says discusses groundsel, and how the plant is attacked by mites.

Groundsel certainly does have a long herbal medicinal history: it was mentioned by Pliny (who called it ‘senecio‘) and by Dioscorides (who recommended it as a cure for kidney-stones). Nowadays, we know that even though canaries do like a nice bit of groundsel seed, humans who take too much of it may well get liver damage. [So perhaps we’ll yet see the Donald recommending it as a coronavirus cure.]

My guess is that Delgado was looking specifically at the last word of the second line (EVA chotols), which he has matched with the -e-e– of ‘senecio’:

My guess is also that Delgado thought that he had seen a reference to “(minutum) reddas”, which some may know from Luke 12:59: dico tibi non exies inde donec etiam novissimum minutum reddas = [King James Bible] “I tell thee, thou shalt not depart thence, till thou hast paid the very last mite” (i.e. the last cent, penny, or farthing). And no, I can’t easily guess which Voynichese word of f6r Delgado thought was “reddas”.

It’s true that spider mites are among the (many, many, many) things that attack senecio vulgaris. But honestly, were any fifteenth century gardeners really that sophisticated about what was (and is) basically a weed?

Perhaps there’s an outside chance that this f6r identification is correct, but to be honest, I’m really not seeing even that much so far.

Nine-Rosette Castle = Amelia?

The decryption that Delgado seems most impressed with is that of the famous castle in the nine-rosette page:

He was so surprised to find the name of the town with the castle – Amelia (in Umbria, formerly Ameria) on this page that he plans to title his book “The Voynich Amelia Manuscript” (i.e. with a deliberate strikethrough).

As justification, he says that the text describes a “carpet of roses” (presumably that’s what the swirl of stars in the middle of the rosette represents?), and that even today there’s an Umbrian festival that has elaborate carpets of roses (he says this is “Spoleto”, but I’m pretty sure he means the Infiorate di Spello).

Spello does indeed have quite a splendidly beautiful festival, even if many of the designs do seem to my eyes to be a little too eager to combine 1960s psychedelia with 1980s crop circles:

Of course, Cipher Mysteries readers will immediately recognise this very specific point in a Voynich theory blog post: the first mention of a specific historical phenomenon. So yes, this is where I would normally point out that the first document mentioning decorating the streets of Spello with flowers (and not even with carpets of flowers) only dates back to 1831.

As a result, my confidence that this is a real decryption is as close to zero as makes no difference, sorry.

BTW, I suspect it is the second word of the Voynichese label just above the castle that Delgado reads as “amelia”, but it’s probably not hugely relevant:

If asked who the greatest historical codebreaker was, would I point to Jim Reeds, Jim Gillogly, or even William Friedman? No! That accolade would surely have to go to Dan Brown’s Robert Langdon.

Like, why? Well, despite the twin handicaps of (a) being accompanied by much younger, sexy sidekicks, for whom his awkwardly lustful old-guy feelings constantly get in the way, and (b) being a thinly drawn fictional character being played by a thinly drawn actor who was much better in ‘Big’, Langdon does solve some kick-ass cipher mysteries. Which is cool.

And so I recently set out to solve the kick-ass cipher mystery that is the Voynich Manuscript using Robert Langdon’s historical cipher playbook as my only guide. And boy oh boy, you’ll never guess where that led…

Birds of a Feather / Flock Together

So how would Langdon begin? Duh! Obviously, he’d turn to the very first page of the manuscript, where an obscure detail (that everybody had looked at before but glossed over) would, in his cavernous brain, trigger some insanely erudite / off-the-wall connection that nobody else could ever make, ever. And he would then have the intellectual courage to follow its trail of breadcrumbs through to its logical end, no matter what awful truth (usually guarded by some millennia-spanning conspiracy) it revealed.

So let’s channel our inner Langdon, and look in the upper left side margin of the first page of the Voynich Manuscript (folio 1r). This is what we see:

“Why, that couldn’t be…”, Langdon would muse, “or… could it?” Yes, it can!

I think you (and Robert Langdon) would surely agree that what is on the first page of the fifteenth century Voynich Manuscript is, without any doubt, essentially the same logo used by Californian children’s faux surf-wear company Hollister. But how? Wasn’t Hollister founded in 1922?

Now, Langdon would immediately know (as sure as if he had Wikipedia open on his leather-bound tablet) that Hollister was a fake brand concocted by Abercrombie & Fitch in July 2000 to help them target a younger market, and that all the talk of it having been created in the 1920s was just made up.

But at this point, Langdon’s eyes would narrow and his forehead would furrow slightly, and he would say something enigmatic in Italian: eppur si muove – “…and yet it moves clothes“. Or something like that.

Despite the logical difficulties, he would be immediately convinced that the two seagulls shared a subtle connection, one that he would have to travel to a long stream of good-looking locations to pursue. After all, what does Langdon ever have to lose, apart from his stellar reputation, his cushty academic job, and the lives of his ex-lovers and oldest friends as they accidentally get caught in the (literal) cross-fire?

And once he had reviewed all the available evidence (say, ten minutes later), he would conclude that there was only one possible way that the propositional variables of the Voynich Manuscript and the Hollister logo could be connected. How? You guessed it – a centuries-old conspiracy one of his nutty old mentors (who probably originally worked with Edgar Wind, but let’s not hold that against him) had once mentioned to him in hushed breath after an exhilarating iconographical lecture at the Warburg Institute… a conspiracy with a terrible, awful, powerful name he could never forget, no matter how hard he tried…

“The Secret Order of the Seagull”

Langdon would also instantly recall that Abercrombie and Fitch had been founded in 1892 by Establishment favourite David Abercrombie, initially selling outdoorsy apparel and related stuff from his Manhattan shop. Yes, Langdon would muse (thinking out loud over a Bellini to an old girlfriend who he had just randomly met on a traghetto in Venice, and who would be sadly heading to her doom in a couple of reels’ time) David Abercrombie was clearly the inheritor of a terrible age-old secret. Look, it’s obvious – you can tell by his moustache and sad mouth, for sure.

But who had been the Grandmaster of The Secret Order of the Seagull before Abercrombie? Well, only Anton Chekhov (not the Star Trek navigator, but the Russian playwright, *sigh*) could fit that bill. And after the disastrous 1896 debut of his play “The Seagull”, Chekhov must surely have sold the dreadful secret he had been looking after to Abercrombie on a outdoors goods buying trip to Moscow.

And yet… might some aspect of the secret also be embedded in The Seagull? In its Act II, which Langdon inevitably has memorized in the original Russian, we find the following:

Nina lingers behind after the group leaves, and Konstantin shows up to give her a seagull that he has shot. Nina is confused and horrified at the gift. […] Trigorin sees the seagull that Konstantin has shot and muses on how he could use it as a subject for a short story: “A young girl lives all her life on the shore of a lake. She loves the lake, like a seagull, and she’s happy and free, like a seagull. But a man arrives by chance, and when he sees her, he destroys her, out of sheer boredom. Like this seagull.

“Now, wait a minute”, notes Langdon to a mysterious young lady who has easily sidled into his stuffy, egocentric life, “I’m sure that’s something I’ve seen in the Voynich Manuscript”.

“I think you could be right”, replies the sexy lady whose paper-thin backstory didn’t really make much sense, now you come to mention it. But given that she arrived at a point when Langdon had his mystery-solving head wedged several miles up his mystery-solving ass, he wouldn’t even have noticed if she had seven heads and ten horns. “It certainly looks like a woman by a lake. Even if she is apparently being eaten by a giant fish.”

Homer, But Not Simpson

But Langdon is wracking his colossal brain yet further, like a Greek fisherman beating squid on a rock to tenderize it. “Why is it”, he asks plaintively, “that Homer compared Hermes to a seagull?”

“[he] sped on over the waves like the seagull that hunts for fishes in the frightening troughs of the barren sea and wets his thick plumage in the brine; like such a bird was Hermes carried over the multitudinous waves. But when he had reached that far-off island he left the violet ocean and took to the land until he came to a great cavern; in this [Kalypso] the Nymphe of the braided tresses had made her home, and inside this he found her now…”

“That’s very strange”, says the young girl, whose curious accent really should have flagged her to Langdon as a strange mix of German rifle champion, Sorbonne arts student and Estonian prostitute, had he not been so distracted by her pert body. “I believe”, she continues, passing him a Beinecke printout from her oddly capacious handbag, “that scene is also depicted in the Voynich Manuscript.”

“Clearly the second nymph from the left is Kalypso”, notes Langdon, flexing his encyclopaedic knowledge of the Classics. “Because, as the daughter of the Titan Atlas, she’s bound to be the fittest.”

“So you have reconstructed The Secret History of The Secret Order of the Seagull, all the way from Homer to Hollister”, sneers the girl, suddenly pointing her diamante-encrusted Mauser HSc at Langdon. “This arcane and dangerous knowledge will do you no good when you are (dramatic pause) dead. As a dead dodo who has died. And is dead.

But just as the conspiracy gun girl is about to shoot, Langdon’s old girlfriend, returning from the bar with their next round of Bellinis, trips on the conspiracy girl’s handbag and falls between Langdon and the gun. She dies, Langdon lives (he is merely grazed by the bullet, of course), the gun girl escapes, and the Secret Conspiracy goes ever on.

You know it makes sense. You’ve read the book, right?

Yes, It’s All As Plain As Day, Fer Sher

So, will the Voynich Manuscript turn out to be linked to some ancient shady symbol-obsessed cabal, of the kind whose dusty evil doors Robert Langdon is doomed to forever find himself accidentally knocking on? Clearly only a fool (maybe even a fool with a History degree) would think otherwise.

Here, I’ve tried to stand shoulder to shoulder with Robert Langdon, letting his indomitable spirit and continent-spanning leaps of faith guide me as we trace the roots of the Voynich Manuscript together. For to one like him (and I can confirm that there are indeed very many like him, because they keep sending me their Voynich Theories, and then snarling that I’m an idiot for not being able to grasp their ineffable brilliance), these things are Easy Peasy.

Perhaps you can learn some important lessons from him too!

Gerard Cheshire’s rehashed 2017 Voynich theory has been through a full media life-cycle this week. Though the newspapers happily collaborated in an emergency Caesarean (ah, it’s a girl), they then swiftly pulled the plug (it’s for the best, poor thing), with the last (w)rites surely not far behind.

Though you might now expect Cheshire to fade away, his optimistic smile still persists. This is because he sees criticisms of his theory as the mechanism by which the self-appointed / self-important Voynich elite protects both itself and the world from his powerful, destabilizing truths.

The Magic Trick

This is, of course, an all-too familiar modern template. Once Claim X lands on our lap (Brexit, Trump, whatever), we find ourselves pressed to decide whether it is (a) outrageous, bare-faced, self-deluding nonsense on a grand scale, where the evidence is twisted to tell a story that appeals to base prejudices, or (b) a heroic outsider movement battling the Establishment, and whose noble cause is simply to Get The Truth Out To The People.

In Star Wars terms, the (small-c) conservative cadre of existing Voynich researchers is thus The Empire, while Cheshire is plucky Luke Skywalker, trying to destroy the collectively entrenched Imperial position: all of which Mustafarian metaphoricity probably makes me Darth Vader. Which is nice.

(It’s a poster you can’t buy, apparently.)

The thing we’re not supposed to notice is the headily polarized either-or-ness of it all (are you Empire or Alliance? Brexiteer or Remainer? Coke or Pepsi? etc). This modern magic trick works by presenting us with two crazy extremes that we somehow have to choose between: in Gerard Cheshire’s case, he presents us with a binary choice between his complex (yet oddly erudite-sounding) Voynich theory and siding with the same self-satisfied Voynich establishment at which he sticks two punky fingers up.

Just as with Coke vs Pepsi, this is a fake two-way choice, particularly given that drinking your own urine might be a marginally healthier third option. Allegedly.

Russell’s Teapot

Actually, this binary mode of presentation has been a mainstay of nutty Voynich theorists for most of the last decade. “If you so-called Voynich experts” (the rant goes) “can’t disprove my theory, then that proves not only that I’m right, but also that you don’t know a damn thing about the Voynich.”

It’s easy, when stripped down and taken so starkly out of context, to see what a hugely fallacious argument this really is, like an epistemological parody of Nietzsche: that which does not destroy my theory makes it True.

This is the burden of disproof, that Bertrand Russell famously likened to claims for an impossibly unobservable teapot orbiting in space. He wrote:

“If I were to suggest that between the Earth and Mars there is a china teapot revolving about the sun in an elliptical orbit, nobody would be able to disprove my assertion provided I were careful to add that the teapot is too small to be revealed even by our most powerful telescopes.”

In space, no-one can hear you ask for cream.

My point here is that whereas in the Olden Days Voynich theorists dished up their shitty theories with a bodyguard of flies (making it almost impossible not to notice which parts really stank), once modern Voynich theorists have done a ten-minute pre-flight check with Wikipedia, they’re ready to launch their theory into a suitably hard-to-reach elliptic orbit.

As a consequence, it has become almost impossible to disprove nutty Voynich theories: all the Voynich theorist has to do is to finesse their story ever-so slightly, turning the impossible back into the highly improbable. Ha! they cry (and some do indeed say ‘Ha!’ at this point), “your efforts to absolutely disprove my theory have now failed, so I must be correct“. And onwards their theory merrily spins, in its far distant elliptical orbit.

Even a Voynich theory as outrageously nonsensical as the Wilfrid-Voynich-faked-it theory (the one that Richard SantaColoma has been peddling for a decade or so) is hard to absolutely disprove. The closest I’ve got is by getting Richard to admit that for his theory to be true, the quire numbers must have been added to the vellum during the 15th century. Even though this makes no codicological sense at all (why give written instructions to a binder about how you want your blank quires to be bound?), who can prove definitively to Richard that this scenario is impossible, rather than merely utterly improbable? And so it goes ever on.

Royal Roads

Nutty theorists also typically believe that it is their coruscant intuition that has given them a shortcut to the hard-for-mere-mortals-to-believe answer: and that it is thus for other (less brilliant but perhaps more meticulous) plodding souls to do the messy follow-on business of joining the evidential start dots to their insightful end dots.

This was particularly true of Nicholas Gibbs’ Voynich theory: this was the one that popped up in in the TLS a while back. (Isn’t now about the time Gibb’s inevitable book describing his brilliant decryption should be appearing?) Gerard Cheshire similarly claimed to have made his giant intuitive leap to the Voynich’s answer in a mere fortnight.

The thing that is wrong with all of this is the idea that there is some kind of Royal Road that will carry you to a quick and easy mastery of the Voynich Manuscript’s secrets. It was Euclid, of course, who famously told the Egyptian ruler Ptolemy I Soter that “there is no Royal Road to geometry”: understanding the different aspects of the Voynich Manuscript before jumping to conclusions is arguably no less a challenge, and one which fewer people every year seem willing to take on.

Daft Ada

And that’s where we are, really: surrounded by Voynich wannabe theorists who fail to do the work, assume the transcriptions are perfect (they’re not), jump oh-so-rapidly to conclusions, use Wikipedia to avoid outright disproof, and then present their nonsensical theory (often to the media) as if it is some kind of inspiring protest vote against existing theorists’ supposed hegemony. Riiiiight.

Me? I’m not Darth Vader, nor even Daft Ada. What kills these stupid Voynich theories isn’t my Sith death grip, but their own lack of a grip on the basic facts. In Gerard Cheshire’s case, he concocts an entire dysenteric proto-language (i.e. one with no obvious grammar or rules), and a spurious timeline entirely at odds with just about everything else: and yet even with all those degrees of freedom to play with, still none of what comes out makes a flicker of sense. What an abysmal waste of time.

And don’t get me started on peer review. Or indeed ‘Ricky Sheeger’… 🙁

In a recent blog post, anthropologist and linguist Magnus Pharao Hansen takes on the Voynich Nahuatl monster constructed by Tucker, Talbert and Janick. Having written a dissertation “Nahuatl Nation” on “the political roles of the Nahuatl language in Mexico and beyond” in 2016, Hansen sounds like someone well equipped for this particular battle. So what does he think?

Hansen helpfully lists the main problems as he sees them, starting with the quality of the actual scholarship supporting the venture:

The most nefarious problem is that it is pseudo-rigorous –  that is it, it works hard to give the appearance of being rigorous scholarship while in fact it is not at all.  They cite lots of serious scholarship, and mostly they cite it correctly, but nevertheless all the citations are used only for circumstantial evidence. As soon as we look at the concrete examples and the readings they are unsupported by this evidence and rests on pure speculation – often uninformed speculation.


But this is just peanuts to space, as Douglas Adams once wrote. For Hansen, the hugest problem is simply that T/T/J’s supposed Nahuatl readings make no sense to him whatsoever:

For me the best problem, best because it is so solid that it clearly invalidates the entire endeavor, is the fact that none of the proposed readings are valid – hardly a single one of the proposed words actually read like a bona fide Nahuatl word.

Many of them are completely alien to Nahua phonological structure. And to be honest I am surprised that the scholars haven’t found it to be odd that a few of the letters are so frequent that they appear in almost all words – for example more than half of the proposed plant names (and names of the nude ladies they call “nymphs”) start with the letter that they read as /a/ – that would be very odd in a natural language, unless the a was a very frequent grammatical prefix (which it isn’t in Nahuatl).

Even so, Hansen pursues the logical thread through to the end by trying to use the supposed ‘key’ supplied in T/T/J’s 2018 book to turn Voynich text into proper Nahuatl, to see where this led. And he ended up no less disappointed by what he found there:

Finally, as I read the example it bothered me that there is a certain repetitiveness in the deciphered text, the same letters seem to occur very frequently in combinations with specific other letters. This is not usually the case for natural languages – but very frequent in something like glossolalia of the baby-speech “lalala balala malalaba”- type.

So, there you have it. There isn’t anything in Tucker, Talbert and Janick’s oeuvre that actually links Voynichese to Nahuatl in any workable way. Next!

If a device could be constructed to reclaim the effort – by which I mean purely physical effort – put into constructing Voynich decryption non-theories, I reckon it could probably power Grimsby (population “88,243 in 2011”, according to Wikipedia) indefinitely. Add in the additional effort expended to construct ad hominems against people who are deemed to be opponents of said non-theories, and you could probably power Cleethorpes (population “nearly 40,000 in 2011”) too.

Sadly, such advanced energy-harvesting technology remains beyond even Silicon Valley’s greatest egos minds, so for now the best we can do is to throw some more theories onto the fire to keep us Northern Hemisphereans warm through the (oddly late) winter chill.

Ata Team Alberta

A four-year-long “family project” (the Ardiç family, i.e. Ahmet Ardiç, Alp Erkan Ardiç, Ozan Ardiç, etc) calling itself “Ata Team Alberta” (ATA) claims (in a YouTube video) that it “has deciphered and translated over 30% [of] the manuscript”, and has submitted “a formal paper of the philological study […] to an academic journal in John Hopkins University.”

The team claims that Voynichese is nothing more than a kind of “Turkic language”, written in a “poetic” style that often displays “phonemic orthography”: they mention f33 as being particularly “rhythmically matching”. Well… anyone who wants to have a look at what they’ve done can fast-forward to 5:02 in the video, which is where their tricksy character correspondence tables start to appear.

Incidentally, when mildly pressed by the Toronto Metro, Lisa Fagin Davis assessed Ata Team Alberta’s efforts as “one of the few solutions I’ve seen that is consistent, is repeatable, and results in sensical text”. Which is, of course, a somewhat peccable (if perhaps slightly maculate) opinion to be holding.

According to this news report, Ahmet is now flying to Turkey to consult with Old Turkic specialists (presumably because all the young specialists are busy). Perhaps he’ll have more to say when he returns.

Gerone Wright

According to Gerone Wright, “it was almost as if I believed in myself that if I studied this text long enough, I would actually know what it means“. And so here’s Gerone telling everyone in the world (via the magic of YouTube) how the Voynich Manuscript is all chemistry, stem cells, genetics, and stuff: and even how some of Q13’s diagrams illustrate ovaries, fallopian tubes and fibroids (etc). Almost, anyway:

The point of including this video here is not that it casts any obvious light on the Voynich Manuscript, but rather that (a) most broadly similar YouTube Voynich theory videos seem to have been done by confused men sitting on cheap sofas in badly-lit sitting rooms wearing only their tighty whities (and that’s not really something that has ‘shareable’ written all over it), and (b) unlike almost everyone in (a), at least Gerone seems to be vaguely aware that what is powering his particular decryption is not so much cryptologic or historical smarts as intense self-belief. Which alone is a rare insight to be blessed with.

Viktor V. Mykhaylov

After sixteen years of effort (yes, four times as much as those Ata Team Alberta wimps), Viktor Mykhaylov of New York has written a book about his Voynich decryption, entitled: Mystery of Senzar. And once again there’s a freshly-minted 2018-vintage YouTube video:

Sample translation of f1r: “Do you graze a goddess-cow? Where? Is this the former deity of the Sun?” And before long: “Have you born this goddess – Eye?”

Aye, indeed. Mykhaylov describes his decryption as follows:

The Manuscript was written in ancient forgotten Senzar language, like mix of Vedic Sanskrit and Devanagari, which was before them – Proto-language. The Manuscript was written in November-December 1417, in Vilnius, by Metropolitan of Kyiv and All Rus-Ukraine, Lithuania, Zhemaytia, Mlodovlakhia (Moldova), Gregory (Gavryil) Tsamblak (Samvlah), and his monks specially for the Queen of Bavaria and Bohemia Sophia, who was the wife of King Wenceslavs IV. This Manuscript was written because Queen Sophia considered herself a goddess Ra.

Metropolitan Samvlah by order of Grand Duke Vytautas, and King of Poland Jagiello, was the head of the largest delegation (about 300 participants) to the Cathedral in Constants. Among all participants were the ambassadors from Saladin – Ayyubid dynasty – An-Nasir Salah ad-Din Yusuf ibn Ayyub.

All of which may be oddly familiar to those who remember John Stojko (“Letters to God’s eye: The Voynich manuscript for the first time deciphered and translated into English”, 1978), who similarly proposed that Voynichese was some kind of proto-language from Ukraine. (I vaguely recall that Stojko lived and died in New York state as well, but I’m not 100% sure of this.) Incidentally, the “Cathedral in Constants” Mykhaylov is referring to here is actually the Council of Constance (1414-1418).

(And yes, I know that Saladin lived from 1137 to 1193. But let’s not bicker over mere details, OK?)

But then Mykhaylov goes and spoils it somewhat by skiing so far off-piste that nobody else can reach him:

Thanks to reading this Manuscript, I received the key to understanding and explaining the origin of all religions, and their names, that existed and now exist, the origin of all tribes and civilizations, and their names, those that existed and now exist, the origin of all languages that were used and that are used now on Earth. I will display all this information in my books, on which I am now working.

Oh well! 🙁

Given that most Voynich furrows have been heavily overploughed over the last two decades, it has become rare for something novel to pop up on my Voynich radar. On those rare occasions such a thing does happen (e.g. the Sagittarius crossbowman, etc), I do try to use my posts to communicate a sense of enthusiasm and excitement.

And so here’s something that might well prove to be interesting: an “Honors senior thesis presentation” courtesy of Adam Lewis at the University of Puget Sound in Tacoma in Washington, entitled “An Anatomy of Failure: Analysis Attempts to Decode the Voynich Manuscript” – 6pm-7pm on 21st February 2018, at UPS’s Wyatt Hall, Room 109.

Incidentally, here’s a picture of the University of Puget Sound’s mascot “Grizz the Logger” in action:

So… why is it that the floor around the VMs is littered with so many dead bodies, so many foolish theories, indeed so many grotesquely idiotic theories? What is it about the Voynich Manuscript that draws out the airiest and least tethered of speculations from people? It’s certainly a topic I’ve thought a lot about over the years, and so I look forward to (eventually) reading Adam Lewis’s senior thesis: it should be fun.

Incidentally, I don’t believe I’ve ever talked with Adam, but I suspect this is his LinkedIn profile here.

On the down side, however, I should point out that the talk is marked as “Campus Only” on the website, so even if you do want to go along, you may not actually get in: hence I’d certainly advise phoning or emailing beforehand if you are considering this.

As a sidenote, fans of Alex Scarrow’s books will probably remember that “Timeriders: The Doomsday Code” features a computer hacker called Alex Lewis, who finds his name hidden in the Voynich Manuscript. That’s probably just coincidental (or possibly some time travelling geocache trickery), but I thought I’d mention it anyway. 😉

(Please excuse the impersonality of what follows, but so many linguistic Voynich theories are popping up at the moment that responding to them all individually would be an even greater waste of my life than trawling through their sad attempts at ‘research’: sorry, hope you understand, etc.)

Dear linguistic Voynich theorist,

Thank you so much for your fascinating [1] and generally well-researched [2] paper. Unfortunately, it seems that in your enthusiasm to publish [3], you may well have skipped past some important details that would have presented your evidence, reasoning, and conclusions in a somewhat different light.

For example, your literature review somehow omitted to mention any of the fifty-plus [4] linguistic Voynich theories that had been published previously: only the most eagle-eyed of barristers would be able to highlight how these differed from yours to any significant degree.

I was interested to note [5] that you repeated the late Stephen Bax’s opinion (perhaps without even knowing that he was the source) that it is OK for linguistic Voynich theorists to disregard all previous statistical and analytical work carried out on the Voynich Manuscript’s text. However, given that almost all of that evidence and observation runs directly counter to your linguistic Voynich theory (and indeed Bax’s as well), it is hard not to draw the conclusion that you have been more than a little [6] selective. By stepping past all the practical difficulties with reconciling Voynichese with natural languages that have been pointed out from 1950s onwards by the Friedmans and many others, it seems as though you have taken a particularly blinkered view of the challenge involved.

As to what you think comprises evidence that supports your particular linguistic reading, I’m sorry to have to point out that neither optimistically plucking words from all manner of dictionaries nor running your fragmentary and non-grammatical [7] output through Google Translate for validation constitutes ‘evidence’ in any normal sense of the word. Instead, these merely show that you are willing to throw darts at a map bindfolded and then claim to have invented the satnav. [8]

Your attempted argument as to how Voynichese’s word-forms structurally map onto the plaintext forms you highlight would have been more persuasive had you looked for evidence beyond the two or three pages from the Voynich Manuscript you restricted your attention to. In reality, had you done so you would have realized that the ‘language’ apparently employed in the Voynich Manuscript varies significantly between sections, between bifolios, and also between different page and line positions (line-initial, word-initial, word-final, line-final, labels, etc): and it turns out that the tiny subset into which you put your time is not at all representative of the rest. So your supposed ‘translation’ fails to scale up in any way at all.

Finally: given that in your paper you were unable to sustain your ‘translation’ of the (supposed) plaintext language(s) of the Voynich Manuscript beyond a handful of somewhat optimistic [9] readings, and that this is almost exactly the same level of (un)convincingness that other near-identical linguistic Voynich theories manage, it is hard [10] to feel persuaded by your claims that you have “finally peeled back the veils of secrecy on this most mysterious of manuscripts“. Instead, it seems overwhelmingly likely that you have fallen headlong into the same shallow logical traps as pretty much every linguistic Voynich theorist ever.

At this point, it would be a wonderful thing to be able to say that despite some methodological flaws and over-enthusiastic leaps to conclusion, your paper has still managed to advance our knowledge of the Voynich Manuscript. But this would not be entirely true. [11] Instead, all you have actually achieved is wasting your own time along with that of everyone else unfortunate enough to read your miserable offering: ultimately, your paper is a bland and tepid mix of pseudohistory, pseudoscience and pseudolinguistics that moves us all backwards rather than forwards in any perceivable way.

Sorry, hope you don’t mind too much, best wishes, etc, Nick

Notes:

[1] This is a lie.
[2] This is a bigger lie.
[3] i.e. “slapdash haste”.
[4] Perhaps even a hundred.
[5] This is an even bigger lie.
[6] OK, “obscenely”
[7] OK, “pathetically nonsensical”
[8] It’s a good job I toned this sentence down, the first draft was a bit too strong.
[9] OK, “laughable and utterly random”
[10] OK, “so close to impossible as to make no practical difference”
[11] In fact, this would be a lie big enough to blot out the sun.