Though the whole idea of metal-clad airships sounds like a steampunk fantasy, they were in fact completely real – the US Navy famously commissioned one (the ZMC-2), and plenty of people tried (and indeed even to the present day continue to try) to build others. And the wonder-stuff that made them possible was that marvellously lightweight metal aluminium.

Here’s my brief guide to the whole genre, plus my thoughts on the 1897 Airship “flap”…

Francesco Lana de Terzi

Historically, the first glimmering of metal-clad LTA (Lighter-Than-Air) flight came circa 1670 (according to Wikipedia) from Francesco Lana de Terzi. He theorised that evacuated metal spheres could provide sufficient lift to float an airship. In reality, if he had built such rigid metal spheres, they would have collapsed under air pressure, but to be fair this was a decent first attempt. And the diagram was cool.

David Schwarz’s Two Airships

By the late 19th Century, materials and technologies had advanced so much that metal airships started to become a genuine possibility. In the 1880s, both the Russian rocket theorist Konstantin Tsiolkovsky and self-taught Croatian engineer David Schwarz realised that a technological sweet spot had opened up. This was building an airship using aluminium (which had been first announced in 1825, and put into industrial production in 1856) and hydrogen (the first hydrogen-filled balloon had flown in 1783).

In 1893, Schwarz produced a test airship for the Russian Army (funded by industrialist Carl Berg) in St Petersburg. The Russian engineer Kowanko pointed out (rightly) that the design’s lack of a ballonet (an extra air bag inside the frame, used to control buoyancy, particularly at take-off) would put a great deal of strain during take-off and landing. And this is indeed what happened – the whole framework collapsed during inflation.

In 1895-7, Schwartz and Berg then built a second airship (this time for the Royal Prussian Government) at the Tempelhof field in Berlin. A test flight in October 1896 was unsuccessful because the hydrogen supplied had been insufficiently purified (and hence provided too little lift). Sadly, Schwartz died (in June 1896, aged 44) before his second metal airship was actually launched: the maiden flight was on 3rd November 1897.

Unfortunately, largely because of structural defects, the airship got no higher than 130m before a combination of problems brought it crashing down, damaging it beyond repair. But… it definitely did fly.

As an aside, Count von Zeppelin later bought all the aluminium used in the ship to reuse in his own (non-metal-skin) zeppelins: the legal agreement he had to sign to do this later gave rise to the myth that he had bought the design rights (which wasn’t true at all).

The 1897 Airship “Flap”

The (ever entertaining, but more than occasionally unreliable) journalist John Keel once wrote a book called “Operation Trojan Horse”. This described a long series of sightings in many US states of a strange airship, almost always travelling by night. This is now generally known as the 1896-1897 airship flap. Keel was convinced that it was, ummm, aliens wot dun it: but given that the descriptions of the people involved tend to be beardy and gentlemanly, this does seem a bit of a stretch.

More recently, Michael Busby’s (2004) “Solving the 1897 Airship Mystery” [I bought the Kindle edition for a very reasonable £4) revisits mainly the Texas sightings from this flap, and draws quite different conclusions.

For example, one contemporary press report gave the names of two men on board the mysterious airship as “S. E. Tillman and A. E. Dolbar”, working for “certain capitalists of New York”. Busby thinks these are Professor Amos Emerson Dolbear and Captain Samuel Escu Tillman; and speculates that the New York capitalists could well have included (gasp) William Randolph Hearst.

Interestingly, a photograph allegedly of the airship taken by a Walter McCann was printed on the front page of the Chicago Tribune, April 12 1897, and also in the Chicago Times-Herald (which I found here):

Might these have been sightings of a metal-clad airship?

C. A. Smith of San Francisco

Matt Novak’s Paleofuture blog mentioned a 1st September 1896 article in the San Francisco Call, reporting that a “Dr C. A. Smith of San Francisco” had a zinc model on display in Market Street of the aluminium & hydrogen airship he hoped to get funding to build. This model had “two wings like those of a beetle” which raised and fell every hundred turns of the airship’s main propeller, along with windows and a door. [Michael Busby’s chapter 19 also includes a 25th November 1896 interview with Smith in the San Francisco Call.]

Some of the observers of the airship reported widely in the 1896-1897 Texas “flap” (see for more about this) described an object having wings “something like that of a bat”. Curiously, C. A. Smith’s 1895 patent includes this drawing, including a distinctive pair of arched bat-like wings pivoted on each side:

At the end of his book, Busby has little doubt that what was seen flying at night in Texas and elsewhere during 1897 was [spoiler alert] C. A. Smith’s airship, just as Smith had promised in 1896. Busby further speculates that Smith (working in California) may have been a member of Charles Dellschau’s mysterious (and possibly hallucinatory) Sonora Aero Club (here’s a link to a nice story about Dellschau in The Atlantic). But… that’s just Busby’s guess, as far as I can tell.

Sumter B. Battey

Still, when a young C. G. Williams (according to a letter in the Dallas Morning News, April 19 1897) allegedly got to speak with the beardy gentleman flying the airship in Texas, the man claimed to have been developing it for many years “at a little town in the interior of New York state”.

This is perhaps where I should add that a 1900 edition of the Badminton Magazine of Sports and Pastimes included a long list of inventors promoting their airships (“navigable balloons”), including a Mr Sumter B. Battey of New York:

C. E. Hite of Philadelphia, John S. Praul of the same city, J. S. Cowden of Virginia, Carl Erickson, Dr C. A. Smith of San Francisco, and Sumter B. Battey of New York. […] Mr Battey’s idea, for instance, consisted of a cigar-shaped balloon of thin aluminium, assisted by wings for upward or downward flight ; the whole thing to be propelled by a series of explosions. At the rear end was a sort of cup opening outward. Into this pellets of nitro-glycerine were to be dropped and exploded at the rate of six a minute, and the ship was to be propelled by the shocks. Mr Battey’s idea is still on the market. Mr Praul’s machine was to have been made of nickel steel and aluminium throughout, including the cylinder or balloon. [p. 429]

Sumter Beauregard Battey of New York patented a neat-looking design for electric bicycles in 1895, so it should be no huge surprise that he also had an airship patent application that was accepted in 1893.

For me, the one oddly distinguishing feature of the airship(s) described in almost all accounts of the 1897 flap was a bright light, much like an electric arc light on the front of the train. So, my own tentative theory – for what it’s worth, and I haven’t seen this mentioned anywhere else – is that what observers took to be a bright light may well have instead been the parabolic dish at the back of the airship that was so distinctive of Battey’s patented propulsion system.

Might Battey’s airship have been the source of the 1897 flap? Though I don’t know so, I think so: if ever there was a nice candidate for a Secret History documentary, this is surely it. My inbox awaits offers from the History Channel etc.

Incidentally, Battey’s address in 1918 (when his son Lieutenant Bryan Mann Battey was reported as missing in action) was “700 West One hundred and seventy-ninth street, New York, NY”, he lived 1861-1934, and his partner was Sarah Angie French. Battey isn’t mentioned in Tom Crouch’s “The Eagle Aloft”, or indeed in any airship history I’ve seen, but perhaps there’s a secret history of airships discussing Battey that I’ve yet to see. Though “Dr S. B. Battey” was a member of the Aeronautic Society of New York, and gave a talk (in 1908?) on wings on dirigibles, please let me know if you see him mentioned anywhere.

Thomas B. Slate’s “City of Glendale”

The 1920s brought a new wave of interest in making metal-clad airships not just possible, but commercially viable. Perhaps most notably, in 1921 Carl B. Fritsche founded the Metalclad Airship Corporation of Detroit (“MAC”), the company that built (as I’ll cover in a separate blog post) the ZMC-2.

But MAC was far from alone. The August 1940 edition of Flying Magazine included an article by J. Gordon Vaeth called “The Blimp Business“, which described a number of other companies who had tried to build metal-clad airships in the 1920s and 1930s.

Thomas B. Slate started up the American Mechanical Engineering Company (an “outgrowth of the Slate Aircraft Corporation”), which in 1928 built an all-metal airship called the “City of Glendale” (“in honor of the city in which it was built” [p.38]).

Though it flew tethered (i.e. as a captive balloon), the Great Depression prevented it from being finished and used commercially: and it was eventually destroyed in 1931. Gordon Vaeth’s description seems to betray a sad fondness for this airship, in that it had a beautifully simple and robust design that could be easily replicated, but that its commercial timing was catastrophically bad.

Carl B. Fritsche and Ralph Upson: the ZMC-2

The history of the ZMC-2 is a huge topic, and this post has already overrun my original target by a factor of 2x or more. So please don’t be cross with me for postponing this to a later date!

National Airship Association of California & Inter-Ocean Dirigible Corporation

Finally, Vaeth’s 1940 article mentions two other companies trying to build radical new metal-clad airships at his time of writing. The first was an all-metal airship designed by Thad Rose for the National Airship Association of California, that had “a prototype under construction”. This contained a clever central tube running down the middle of the airship, creating a vacuum at the front of the ship, pulling it forward. A Russian website I found points to a large article in the April 6, 1939 Los Angeles Times (which I haven’t yet seen), plus a screen-grab of Rose’s 1930 patent. You can see the distinctive power tube running down the centre:

The second was the Inter-Ocean Dirigible Company, which was a Virginia-based company that grew out of the Virginia Airship Company. This, too, incorporated a central (internal) power tube running from end to end: special nozzles at the inlet and outlet of the power tube “enable[d] control of the ship in any direction”. Sadly, I haven’t yet found a patent drawing or picture of this particular airship; but there’s a good chance that it was never actually built.

Your Thoughts, Nick?

The neat-and-tidy Wikipedia page on metal-clad airships is all very well, but I do suspect the succession of airships described above points to a much more interesting history. And who knows, perhaps this will also include the secret history of the 1897 airship flap?

Would it surprise me if I’m currently the only person in the world who genuinely wants to know exactly what Thomas Greenhow Williams (‘Tex’) Settle’s US Navy timeline was? No, of course it wouldn’t. So why inflict it on the world as a blog post? Too late, here it is!

Naval History Division

Settle’s US Navy biography was compiled by the Navy Office of Information Internal Relations division (OI-430), 1st April 1969. Putting all the balloon races and free-ballooning stuff (and everything that happened on the USS Portland in WWII) to one side:

  • 6 Jun 1918 – commissioned Ensign with the class of 1919, having graduated with distinction
  • Jan 1920 – reported for duty in connection with fitting out the USS Whipple (in Philadelphia)
  • 23 Apr 1920 – served as Engineer Officer on the USS Whipple, then as Navigator, then as Executive Officer
  • April 1922 – Postgraduate School, Annapolis, MD for aviation radio engineering, before continuing the course at Harvard University (gained Master of Science degree in June 1924)
  • Jul 1924 – reported for duty at NAS Lakehurst, NJ on board the airship USS Shenandoah, and then on the airship J-3
  • Oct 1924 – served on airship USS Los Angeles as Communications Officer, Engineering Officer, Navigator, and Executive Officer.
  • Feb 1929 – assigned to the Bureau of Aeronatics, Navy Department, Washington DC
  • Jul 1929 – served at the Goodyear Zeppelin Corporation, Akron OH as Inspector of Naval Aircraft during construction of USS Akron and USS Macon.
  • Jan 1934 – served as Training Officer as NAS Lakehurst, NJ
  • Jun 1934 – assumed command of the USS Palos (ship) in the Yangtze Patrol of the Asiatic Fleet
  • Winter 1934 – Senior Naval Officer and Acting Consul at Chungking
  • Jun 1935 – assumed command of the USS Whipple (ship)
  • Feb 1937 – became Fleet Communications Officer on the Staff of the Commander in Chief, Asiatic Fleet
  • Jun 1938 to Jun 1939 – served as Executive Officer of NAS Lakehurst
  • 1939 to May 1940 – on senior course at the Naval War College, Newport RI
  • May 1940 to Apr 1941 – served on the Staff of the Naval War College, Newport RI
  • May 1941 – Chief of Staff and Operations Officer for Commander Cruiser Division TWO, Atlantic Fleet
  • Aug 1941 – Chief of Staff and Operations Officer for Commander Cruiser Division EIGHT and for Commander Cruisers, Atlantic
  • May 1942 – worked in the Bureau of Aeronautics and the Office of the Chief of Naval Operations, Navy Department, Washington DC.
  • Sep 1943 – in command of Fleet Airships, Pacific, and then of Fleet Airship Wing THREE
  • 3 Mar 1944 – assumed command of USS Portland at Eniwetok. For this command, he was awarded the Navy Cross, the Legion of Merit with Combat “V”, and the Bronze Star Medal with Combat “V”.
  • Jul 1945 – temporary duty at Headquarters of Commander in Chief, US Fleet, Washington DC
  • Aug 1945 – reported to Commander in Chief, Pacific Fleet.
  • Sep 1945 – a task force under his command evacuated ~1500 POWs and internees from the Japanese Mukden camps. He then took the surrender of Japanese naval forces in Tsingtao, China.
  • Nov 1945 – Task Force Commander of Commander Cruiser Division SIZ, and then Commander North China Naval Forces.
  • Jan 1946 – took command of the Yangtze Patrol Force
  • May 1946 – assumed command of Amphibious Group THREE.
  • Aug 1946 – reported as Chief of Naval Airship Training and Experimention (CNATE) at NAS Lakehurst, NJ
  • Sep 1947 – became Chief, Naval Group, American Mission for Aid to Turkey (arrived in Turkey in Jan 1948)
  • 16 Oct 1949 – returned to Office of the Chief of Naval Operations, Navy Department
  • 6 Feb 1950 – designated Vice Chief of Naval Material, Navy Department
  • Jan 1951 – took command of a Joint Army, Navy, Air Force Task Force for a classified project
  • Aug 1951 – Commandant of the Eighth Naval District (in New Orleans, LA)
  • 8 Mar 1954 – Commander Amphibious Force, US Pacific Fleet
  • 20 Aug 1956 – Chief of the Military Assistance Advisory Group, Oslo, Norway
  • Oct 1957 – ordered to Third Naval District for temporary duty prior to retirement
  • 1 Dec 1957 – transferred to the Retired List of the US Navy, rank of Vice Admiral
  • 12 Feb 1962 – ordered to return to active Naval service, joined a Defense Study Group on Military Compensation, Office of the Secretary of Defense, Washington DC
  • Oct 1962 – assigned to the Bureau of Naval Personnel, Navy Department.
  • 1 Jul 1963 – released from active duty
  • 26 Aug 1963 – headed the board on Warrant Officer, Limited Duty Officer, and Senior Chief Petty Officer Policies in the Bureau of Naval Personnel

BuAer / NAS Lakehurst / Office of the Chief of Naval Operations

The specific reason I compiled this timeline was so that I could see exactly when Tex Settle was working at BuAer and NAS Lakehurst:

  • Jul 1924 to Jan 1929: NAS Lakehurst
  • Feb 1929 to Dec 1933: Bureau of Aeronautics
  • Jan 1934 to May 1934: NAS Lakehurst
  • (…gap…)
  • Jun 1938 to Jun 1939: NAS Lakehurst
  • (…gap…)
  • May 1942 to Sep 1943: Bureau of Aeronautics and Office of the Chief of Naval Operations
  • (…gap…)
  • Aug 1946 to Sep 1947: NAS Lakehurst
  • (…gap…)
  • Oct 1949 to Dec 1950: Office of the Chief of Naval Operation

The last Cipher Mysteries post (from Jo) on Hickey Taylor only had a single scratchy picture of him playing bridge backstage. However, this lack of good images prompted CM commenters to dig up a whole sequence of pictures, which I thought would be good to put into a photo timeline.

Photo Timeline

1929 “Desert Song”, found by milongal:

1930 “Whoopee” (found by Jo):

“En tour Hickey […] outside Mark Foy’s, Sydney 5.30 A.M., [ca. 1930]” (found by Jo):

193x “St Joan” (found by Jo):

1937 Sydney Sun, playing bridge backstage with the cast of “The Merry Widow”:

1945 “Desert Song” (found by Thomas):

Back to the Family Photo…

Going back to the whole family photo affair, was it really Hickey Taylor whom Charlie Webb (circled) was pranking? Personally, I don’t see it at all, but… what do you think?

(Nick: here’s a guest post [lightly edited to house style] from Melbourne-based Cipher Mysteries commenter Jo, introducing Hickey Taylor to the Somerton Man discussion. Over to you, Jo…)

Stuart Webb recently re-posted “the family photo” on Derek Abbott’s Facebook page, along with a query about one of the people on it: Hickey Taylor.  My first reaction was that “Hickey” and “Taylor” sounded like two old farmers from Camperdown (there are lots of Hickeys and Taylors there…) but commenter Poppins cleverly pointed out that Hickey Taylor was in fact a stage manager and occasional actor for J.C. Williamson’s. So… who was Hickey Taylor?

Henry Herbert “Hickey” Taylor, 1903-1962

Though born in Tasmania, Taylor’s electoral roll enrolment address across several decades is his parents’ home at 56 Surrey Road, South Yarra, right up to his death in 1962, when he was living with his widowed mother, Isabel. He spent long periods away from South Yarra with his work.

Taylor’s AusStage listing has him as being in Adelaide from the late 1940s to late 1950s – however, this was as an actor up until 1947, and then as a stage manager from 1949. If you dig through J.C. Williamson’s programs [he joined the company in 1925], you can also see that he spent long periods in Perth, e.g. as stage manager for “The Girl Friend”.

Perhaps most intriguingly, he was also the stage manager for the Adelaide run of “Under the Counter”(but not the Melbourne run), which ended on 30 November 1948. This, of course, places him in Adelaide at the time of Carl Webb’s death.

It seems that Hickey Taylor may also have been a drag performer, or to use the language of the 1940s, a female impersonator.  The Australian Queer Archives has an interview listing [p.66] (I haven’t yet managed to secure a listening appointment but have contacted them and am trying, hopefully with Poppins).

Taylor worked in his stage manager capacity with some of the most celebrated Southern Hemisphere female impersonators of the time  – e.g. Phil Jay and John Hunter of the Kiwi Revue shows.

As an aside, there have been books (and even Masters theses!) on the soldier female impersonators – theirs was a skilled and well regarded craft. They could also often be a tough bunch. Brent Coutts’ book “Crossing the Lines” is probably the most comprehensive review of the Kiwis.

I viewed Hickey Taylor’s probate document, as well as his hospital death report from the Alfred Hospital at the Public Records Office of Victoria. He died of heart complications – an unexpected death of septicaemia – in 1962.  (I’m still digesting the report and will send my photos to Nick.)  Dr Colin Ernest Seabridge, the Alfred Hospital’s Resident Medical Officer wrote “I find it impossible to state the cause of death.” There are a lot of similar words and phrases to Charlie Webb’s death and inquest documents.

Taylor was known to the hospital, he was “a depressive, with suicidal tendencies”.  He had been “under psychiatric treatment.”

He left his estate to his widowed mother and his brother and sister, this included two houses – 34 and 36 Fawkner Street, South Yarra (worth a small fortune now!)

Connections and Speculations

Was Hickey Taylor the source of the Rubaiyat of Omar Khayam? (Commenter Em and I believe so!).  We know that it was printed by New Zealand company Whitcombe and Tombs and that an identical copy has never been found.  (Was it a limited army print run?)  I haven’t been able to find Taylor on any New Zealand Immigration and Passenger lists in the 1940s, so I would say if the Rubaiyat came via Hickey Taylor it might well have been via a Kiwi Revue member, such as renowned female impersonator Phil Jay, who played in the same cast as Taylor in “The Girlfriend“.

We know that Charlie was fond of solving Norman McCance’s newspaper bridge problems, but there’s also a picture in the Sydney Sun of Hickey Taylor playing bridge in 1937:

We can hypothesise about the relationship between the two men and also about Carl Webb’s manicure, careful shave, well-developed calf muscles and wedge shaped feet, noted at the time of his death. We could speculate whether this was the end of an affair, an assisted suicide or a case of moving a dying Charlie somewhere where he could be found without linking him to his theatre friends. Perhaps someone else deposited the suitcase at the station? If we think about the laws and climate of the time, an anonymous death makes a certain amount of sense: Victoria only removed the death penalty for sodomy in 1949. It was only between 1975 and 1997 that Australian states and territories gradually repealed their sodomy laws and began gay law reform.

It also appears that Carl may have told his family he was in Cottesloe, working as an electrician, as per the solicitor’s advertisement regarding Gladys May Scott’s will (posted on Derek Abbott’s Facebook page by Lachlan Kelly). Where was Carl between the end of 1946 and November 1948 and what was he doing?

The Tidying-Up-At-The-End Bit

I think the first Cipher Mysteries post I ever read was “On Carl Webb, Truth and Beauty” (5 August 2022) where Nick warned us against “The one true narrative”:

Maybe we can now each spin our own tidy yarn tying together personally preferred loose threads…But… by doing this, I think we’d be dancing around some sinkhole-sized gaps, not in our preferred story (which will always sound nice to our own ears), but in Carl Webb’s actual story.

What was the American connection? Had Webb travelled to America? Did Doff give Webb the Rubaiyat? Did Webb have a replacement partner lined up? Might he actually have been gay, and married Doff to hide his sexuality? What instruments did he make … Did he have a police record?

My own interest here was first sparked when Bromby Street was mentioned: I initially felt sure the Somerton Man case had something to do with signals intelligence (there were at least fourteen different signals intelligence related sites in the local area during World War II). But I think we should now add a relationship with Hickey Taylor to the list of possible narratives to consider. Might the story have more in common with that of poor Alan Turing, needlessly persecuted because of his sexual preference for men?

I suspect this one may have legs (with well-defined calf muscles?).

Finally: thank you John Sanders for initially pointing out that Gerald Keane had travelled to New Zealand – I think that put us on this track, and thank you also Poppins for finding Hickey Taylor.  Punters: keep the commentary “noice” or Aunty Jack will “rip your bloody arms off!” (Sorry Nick, Aunty Jack is an old Australian reference, from before my time here!) And thanks Nick for promoting my comment to a post; it gives a good opportunity for further sleuthing and mature reflection.

Much as I’ve enjoyed looking through old J. C. Williamson programmes and Melbourne bridge columns hunting for Gerald Keane and Carl Webb, I can’t help but wonder if it’s time for a new research angle.

I mean, tracking Dermott Derham ‘Derry’ George (of 13 Wandeen Road, S.E.6, mechanic in 1939 Victoria census) and his wife Rita Mabel (nee Dixon, married 1942 in Victoria, maybe at Hoffman’s Road, Keilor, home duties in 1946 Victoria census, died in Keilor in 1998), and I guess his brother Dermott James George and Olga Burge George (both at 13 Wandeen Road in 1939, and again in 1941) is all very well, but it’s not really much of anything. Oh, and driving in his 746 c.c. M.G.J. in 1935, and his M.G. J4 in 1937 and 1938 and 1938 again for the Light Car Club? Nope, not that gripped, sorry.

So what’s next?

Masonic Registers and Card Indexes, maybe?

This is what I’m thinking might possibly give us a lead on Gerald Keane and/or Carl Webb.

There’s a whole load of Australian Masonic Registers and Card Indexes 1830-1991 now being digitised and prepared for publication on familysearch.org, which is just the kind of thing I like to trawl through just in case. (But it’s not up yet.) Similarly, the Museum of Freemasonry in NSW also has digitised a lot of its Masonic records, though these are not yet available online. Still, you’d have thought the Adelaide Masonic Centre Museum at 254 North Terrace, Adelaide and its Grand Lodge Library (the J. R. Robertson Masonic Memorial Library) might have something like the card indexes each Lodge had, right?

Wrong! Because it turns out that tons (almost literally) of masonic registers and card indexes from South Australia have been lodged (if you’ll excuse the pun) in an Australian archive, including a downloadable finding aid listing all the individual documents – I know because I actually read it a few months back. But… I have since lost my copy of that file and now can’t find it again. Which is unbelievably annoying.

So, can anyone help me find this document again?

Royal Adelaide Hospital

Carl Webb was not a well man. At the time of his death, he had an enlarged spleen (which must surely have been hugely painful), and it appears (from his hair) that he had been exposed to dangerously high (and as yet unexplained) levels of lead some 2-3 weeks before his death. Moreover, it seems likely to me that what killed him was an overdose of heart medication (though whether that was self-inflicted, deliberate, or merely accidental is a quite separate issue).

TL;DR – Carl Webb was not, as the phrase goes, a happy bunny.

Hence, I’ve long wondered whether Webb might have been admitted to (and discharged) from a hospital in the month before his death – and given that he was found on Somerton Beach, I’ve specifically wondered about the Royal Adelaide Hospital.

Interestingly, the admissions register for the RAH have been digitised up to 1961, and are accessible up to 31st December 1936. These look like this:

Now, it’s not clear to me when (or to whom) the Admissions Register scans covering November 1948 will/are be accessible. There seems no obvious reason why film # 102936290 isn’t available online, but might it be accessible in person via an LDS Family History Centre? Perhaps someone here will know what the deal is (because I certainly don’t, alas).

Update!

Though Google wasn’t as helpful as normal, I eventually found a copy of the missing document in my mobile phone’s pdf cache. It was SRG 490, “Grand Lodge of Antient, Free & Accepted Masons of Australia”, held at the State Library of South Australia. More to follow when I’ve gone through it properly…

I’ve recently had some nice correspondence with Rafał Miazga, an independent Polish researcher who, having deftly avoided getting trapped by the perils of Voynich Manuscript research, instead travelled deep down the Rohonc Codex rabbit-hole. He has posted up a (substantial) paper on academia.edu outlining both his research and his interesting (yet tentative) conclusions, which I think are well worth reading. I also thought it would be worth using this post to summarise my very high-level view of the state of play of Rohonc Codex research, plus why I think Rafał’s paper is particularly interesting.

Kiraly and Tokai

After many years of only stumbling advances, Rohonc Codex research is now broadly dominated by the work of two researchers, Lev Kiraly and Gábor Tokai. Even though Kiraly and Tokai haven’t fully published their research, there seems little doubt (even from Benedek Lang) that they are heading in the right direction with the meaning they are extracting from sets of Rohonc Codex words.

And yet their results remain highly bemusing, incomplete, and unsatisfactory. For them, Rohonc Codex words have no obvious declination or conjugation (so are more like English than Latin), and largely lack structure (many passages are more like repetitive babble than structured text).

Overall, I think it’s fair to say that K & T are trying to solve the puzzle of the Rohonc Codex from the details upwards, i.e. as a pure linguistic / syntax / grammar puzzle. But right from the start, it seems to me that they’ve been tangled in ‘word weeds’: like the Voynich Manuscript, the Rohonc Codex presents many repetitive babble-like features (though admittedly not quite at the same level), and K & T seem to be perpetually stalled by these.

Ultimately, they need the Rohonc Codex’s text to be a pure language for their methodology to work, but looking in from the outside I find it hard not to conclude that the two don’t quite fit as well as they’d like. I’ve thought from pretty much Day One that they’re missing some kind of higher-level hypothesis: they know how it works, but they can’t quite say what it is. For them, the Rohonc Codex remains an isolate, i.e. “an individual socially withdrawn or removed from society” (Merriam-Webster), and so they struggle to draw parallels or connections with other languages, other historical artefacts, or other histories.

Enter Rafał Miazga

What Rafał Miazga did is compile his own transcription, and then draw his own low-level conclusions which were largely parallel to Kiraly and Tokai (though there are many overlaps, they’re far from identical). What they do seem to me to broadly share is that the Rohonc Codex is both a religious mess (i.e. one that doesn’t quite match ‘proper’ Bible stories) and a linguistic mess. On balance, I think it’s fair to say that Rafał’s word-level account of the Rohonc Codex isn’t at all far from what Kiraly and Tokai put forward.

But here’s the big difference: Rafał also has an idea of what he strongly suspects the Rohonc Codex is – which is (probably summarising too boldly and quickly) a book written down by a profoundly deaf monk in an idiosyncratic language. That is, the Rohonc Codex is (in some way) a sign-language transcription, with a large code-book (nomenclatura) of specific signs.

This is a very bold idea, and one that I think Rafał should be commended for, as well as encouraged to explore further. Well done Rafał, keep going!

Nick’s thoughts

In some ways, what Rafał has achieved could well be a kind of Rohonc Codex “plot point” (i.e. that pivots the narrative and spins the story off into a new direction), in that it suggests other histories to look at.

For example, monks who had taken a vow of silence (Trappist, but also Cistercian and Benedictine) had their own monastic sign languages. There are plenty of websites where these are mentioned or discussed: I believe that there is a decent (if dispersed) literature on these. There are even YouTube videos where monastic sign languages are mentioned:

The primary historical question for me is therefore whether there are any other examples of transcribed monastic sign languages mentioned in the literature. I’ve suggested this to Rafał and I’m sure he will be looking for these. There are certainly partial word-lists out there, but might there be other texts?

More generally, I suggested to Rafał that he might think about looking at the Protestant Reformation in Hungary. This was a hugely complicated time for Christianity, where Catholicism, Protestantism and Unitarianism were all prominent players, with many Diets trying to broker accommodations (both religious and political) between them. This tangled picture seems to me to be mirrored by the Rohonc Codex’s own tangled religious tropes: so perhaps its author was a profoundly deaf monk whose religious rug had been pulled from under him by the Protestant Reformation?

In many ways, what a hypothesis like Rafał’s offers isn’t necessarily complete answers, but rather a way of looking at historical sources with new eyes. With luck, this might prove to be the start of a fresh chapter for the Rohonc Codex. Fingers crossed!

Some Cipher Mysteries commenters have speculated that Gerald (Jerry) Keane’s job at J. C. Williamson’s might have connected him to the run of “Under The Counter” at Adelaide’s Theatre Royal in November 1948. But is there any actual evidence of this? Keane doesn’t appear in the UTC programme, so why should we think this is so?

From Chief Mechanist to Caretaker…

As commenter Poppins pointed out, Jerry Keane was the Chief Mechanist for J. C. Williamson’s 1937/1938 production of Victoria Regina. He was also the Chief Mechanist for the (Melbourne-based) Borovansky ballet when they went on tour in New Zealand in 1944: so I think we can reasonably presume that he was the Chief Mechanist on tour with the two production companies.

Yet at the time of his accidental death in 1960, Keane was working for J. C. Williamson’s “scenery store situated at 47 Richmond Terrace, RICHMOND as a caretaker and a storeman, and his duties were to see that the premises were secure at night and the Firedoor was closed at night” (as deposed by his fellow theatrical employee Edward James Morgan of 1 Kennedy Street, North Richmond). Which, given that he seems to have started as a caretaker in the Camperdown Mechanics Institute back in 1915, would seem to have Fate bringing him full circle back to where he began.

Maybe the Borovansky Ballet?

So, what was Keane’s job at J. C. Williamson’s in late 1948? We also now know that the Borovansky Ballet were popular with Australian audiences and continued touring for many years after: two productions from this time were Terra Australis (1946) and The Black Swan (1949). So it is entirely possible that he continued in his role as Chief Mechanist with the Borovansky Ballet throughout this period.

Interestingly, the NZ national library has a page listing all the ballet programmes it has for 1947, which (as you’d expect) has numerous performances by the Borovansky Ballet. This includes this lovely cover:

The NLA has plenty of photographs for the Borovansky Ballet, of which this one is my favourite (backstage for Swan Lake, 1947, taken by V. Gadsby):

However, the corresponding NZ page for 1948 has no performances at all by the Borovansky Ballet, but many performances by Ballet Rambert in association with J. C. Williamson’s (from May 1948 to June 1948). The NZ page for 1949 has none at all for either ballet company. Yet even though Ballet Rambert performed in Adelaide in November 1948 (i.e. immediately before “Under the Counter”), I saw no sign of Jerry Keane in the programme for their performance there.

Perhaps some intrepid soul will find something similar to J. C. Williamson’s Salary Book 1933-1943 (first mentioned here by one of the many ghosts of Steve Hurwood), but for 1947-1949?

Maybe “Under The Counter”?

It’s entirely possible that someone will find Jerry Keane mentioned in travel records relating to Cicely Courtneidge’s “Under The Counter” production as it finished its mammoth four-year tour in Adelaide in November 1948. So… what happened?

The performances prior to Adelaide had been in Perth, though some performances that were due to happen in Kalgoorlie after that were unfortunately cancelled “because of the coal strike“. I should perhaps note that the Perth “Workers Star” described the (admittedly fairly lightweight) show as “reactionary twaddle“:

CICELY Courtneidge’s show, Under the Counter, in Perth now, is a dirty piece of boosting for blackmarketeers, and squeezes in a few reactionary cracks at the British Labor Government and the Communists. Stooping to this kind of reactionary twaddle won’t get the big theatre magnates anywhere with Aussie audiences. They obviously found the show very boring, it hardly raised a laugh. The night the Star reviewer went His Majesty’s showed so many empty seats the box office must have made a loss on it.

The main body of the company travelled by train from Perth, arriving on Monday 15th November 1948, just a few hours before the performance. Cicely Courtneidge’s accompanist Robert Probst (who later got into hot water for disparaging the quality of Australian orchestras) flew to Adelaide on Saturday 13th November 1948 to rehearse on the Sunday. (Though Cicely Courtneidge herself may have flown on Friday 12th.)

Courtneidge went shopping on the 22nd to buy some pyjamas to take back for her husband (no, I’m not making it up), and after the show’s run had finished, went to stay at a bookmaker’s house on Palm Beach with her main man Thorley Walters. The Sydney Truth gleefully reported:

When Cicely Courtneidge and Thorley Walters left for home during the week, Palm Beach lost two of its most colorful visitors. Cicely used to prance into the surf in a bright yellow brassiere top with bright royal blue trunks and Thorley had a pair of orange trunks which used to glow in the dark. Cicely was forced to put splits in the sides of her shorts as her avoirdupois increased (she admitted putting on a stone and a half in Australia). As the sun sank to rest below the purple hills at Palm Beach Thorley’s trunks became more of an illuminated address and the sight of his luminous posterior bobbing about in the briny is some thing the locals won’t forget for a long time.

Courtneidge flew to Melbourne on 29th November 1948; and later, after a farewell party at Prince’s, she flew to Honolulu on 17th December 1948.

Thanks to Cipher Mysteries commenter Poppins, we now know that Carl Webb’s close relative Gerald Keane was known as Jerry Keane. This was from the souvenir programme for a J. C. Williamson production of “Victoria Regina” that ran from 1937 to 1938 (the file is dated October 1937, but the front cover has the hand-written note “Auckland NZ 1938”). Page 10 has a list of the “Heads of Stage Departments”, one of whom is:

So let’s have a look at Jerry Keane.

Gerald Thomas “Jerry” Keane

Gerald Thomas Keane was born in Ballarat East, Victoria in 1889: in 1915, he married Freda Grace Webb (1896-1964, sister of Carl Webb) in Victoria. There’s a 23 Jan 1915 news report of Gerald and “the Webb sisters” performing in a local concert. This was also the year he lost his job as caretaker of the Camperdown Mechanics Institute, as per this letter of 14 Aug 1915.

It seems that it wasn’t too long before he found employment with J. C. Williamson for, as commenter Francis pointed out, there’s an article from 20 Jul 1940 in the Camperdown Chronicle that says:

Mr. Gerald Keane, son of Mrs. Keane, of [130] Manifold street, who has been on the staff of J. C. Williamson for over twenty years was in Camperdown on Thursday, on a visit to his people. Mr. Keane has had an extended trip with the Russian ballet, visiting Adelaide, and then Brisbane.

Gerald and Freda had three children: Leo Vivian (born in Camperdown in 1915), John Russell (‘Jack’) (born in 1917), and Gwendoline Mary (born 1919). In 1943 (when his son Jack died), the family address was 194 Stewart st, East Brunswick, Victoria: before that, they lived at 226 Glenlyon Road (this was their address on Boxing Day 1940 when they were witnesses for Roy Webb’s Will). As commenter Jo pointed out, Carl Webb appears to have been living with the Keane family at that time (i.e. not long before Carl’s marriage to Dorothy).

In 1944, Gerald (“Jerry”) Keane was reported as winning £10 in a lotto in Launceston:

WHEN certain lottery prizes were announced in Launceston on Tuesday, two very excited people were prima ballerina, Dorothy Stevenson, of the visiting [Borovansky] ballet company, and Jerry Keane, chief mechanist accompanying the ballet. Hear that these two visitors collected £10 each.

The Borovansky ballet company was based in Melbourne, founded in 1939 by Edouard Borovansky and his tall wife Xenia as the “Academy of Russian Ballet above a shop in Elizabeth Street”, whose studios then (from 1940) provided the home for the Melbourne Ballet Club. According to this page:

The year 1944 brought two landmarks for Borovansky: he became a naturalised Australian, and J.C. Williamson’s backed an Australian tour that took his company from Melbourne to Adelaide, Hobart, Launceston, Sydney and Brisbane, and then to New Zealand. From then until 1961 – except for occasional unfortunate breaks – the Borovansky Ballet was a permanent and popular feature of J.C. Williamson’s programming […]

Over the years, highlights of the repertoire included Laurel Martyn’s Sigrid (first presented by Borovansky in 1940), Petrouchka (1951), the complete Sleeping Princess (1952), Massine’s Symphonie Fantastique (1954), Cranko’s Pineapple Poll (1954) and, from Lichine, a full-length Nutcracker (1955) and the specially-commissioned Corrida (1956). Borovansky himself explored Australian themes for three original ballets, Terra Australis (1946), The Black Swan (1949) and The Outlaw, a 1951 retelling of the Ned Kelly saga – proving that Borovansky had become, in his own words, ‘a dinkum bloody Aussie’.

[…] Borovansky’s papers and a striking self-portrait are held in the National Library of Australia.

(PS: ballerina Dorothy Stevenson was the daughter of the Bishop of Grafton. So don’t say I don’t spoil you for interesting historical facts.)

Gerald died in 1960 in Fitzroy, Victoria.

Chief Mechanist

In a touring company (usually ballet or opera, but sometimes musicals and larger productions), the Chief Mechanist (or Head Mechanist) typically reports to the Production Manager, and handles planning, logistics and staff rostering, to ensure that each night’s performance does exactly what it is says in the souvenir programme. Hence Jerry Keane “accompanying the ballet” company on tour as its Chief Mechanist makes perfect sense.

Compared to theatre productions, where Stage Assistants (and sometimes “Mechanical Staff”) typically report to a Stage Director, the role of a Mechanist would involve wrangling not just the stage but also (in modern productions) flying harnesses, animatronics, and all manner of special staging effects. You can therefore think of the Chief Mechanist was kind of a techno-magician behind the scenes, turning a performance into a memorable production.

If you’ve previously looked at the final page of the Voynich Manuscript (f116v), you probably know exactly what I’m talking about here: the strange marginalia / pen-trials / whatever that aren’t Voynichese, but aren’t obviously anything else either. The middle two lines of “michitonese” are interspersed with crosses, making them resemble a prayer or protective charm (when reading these out, you’re supposed to make the sign of the cross when you see a ‘+’). The two michitonese words I’m going to focus on today look like “ahia maria“, which is what “Saint Mary” would sound like in Greek. But is that what they really say?

Parsing the page

To my mind, the initial challenge is working out not how to read the page (Lord knows we don’t need yet more speculative michitonese decipherments), but rather how to parse the page. Knowing that crosses are a structural feature of prayers and charms is a helpful start, but I suspect that differences in inks and letter shapes are also key things to bear in mind.

I discussed this page in The Curse of The Voynich (2006), and proposed that what we are often seeing here is a page whose writing had faded so much by the time that a later (in fact, probably much later) owner looked at it that they felt compelled to emend it before it disappeared completely from sight.

Along those same line, I’ve previously wondered whether the first two words of the pair of lines (which have been immortalised as “michiton oladabas”) might originally have read “nichil obstat”, before fading almost to nothing and being emended into their current state. This isn’t just a matter of ink density, as some people have suggested: for example, the ‘l’ of oladabas looks like it was written by a 15th century quill pen but the ‘n’ of michiton looks to me like it was written by a 16th century metal nib. And if you compare all three ‘a’s of oladabas, you’ll struggle to work out which is original and which is emended. (For what it’s worth, I believe the middle ‘a’ is original and the other two are emendations.)

So broadly speaking, I feel that the first thing we have to do is parse “ahia maria”, i.e. try to work out which parts of it are original and which are likely later emendations.

Multispectral scans

Though we only have (frankly shocking) quality multispectral scans of f116v that were left on the Beinecke’s file server several years ago, these are vaguely helpful here. Here’s what I was able to salvage from “Voynich_116v_WBRBB47_108_F.jpg”:

Though this is hard to make out, it suggests that the final ‘a’ of (what looks like) “ahia” wasn’t emended, but the rest of the word was. The first “ma” of “ma+ria” also seem to have been worked on.

In general, it seems that we can probably trust that the “ma+ria” part was what was originally written, but we need a bit more insight before we can come to a conclusion about the “ahia” part.

The History of Hail Mary

Given the prayer-/charm-like context, it would seem very reasonable to hypothesise that the two words might originally have read Hail Mary (in some language). But when did people start saying Hail Mary?

The Greek form (which begins Θεοτόκε Παρθένε, χαῖρε, κεχαριτωμένη Μαρία, ὁ Κύριος μετὰ σοῦ. ) developed independently of the Latin form “Ave Maria, gratia plena“. The latter took shape around the turn of the first Millennium, with Thomas Aquinas noting that the biblical original (“Ave, gratia plena“, from the Gospel of Luke) had had the word “Maria” inserted. The Latin form first appeared in print in 1495 in Girolamo Savonarola’s “Esposizione sopra l’Ave Maria“.

In terms of what forms of Hail Mary we might reasonably be looking to find, then, the Greek version is distinctly unpromising, while the Latin is very much limited to Ave Maria.

Yet if you search for medieval Latin charms that mention Mary, you’ll find a good number that invoke her name (e.g. “+ sancta Maria peperit +” in CUL Additional 9308, folios 49r-50r, mentioned here, footnote 155), often when hoping to ensure a good outcome from childbirth.

Additionally, “Maria Maria” appears doubled in a particular branch of Gaudendum nobis est (see MSS A-GU 30, CH-EN 1003, CH-EN 102, and Stuttgart 95, mentioned here, Table 4-6, which are from Engelberg and Lambrecht). We’ll see why this is relevant in the next section…

The Other Maria(s)

We have to be careful that we don’t let people’s prior readings over-influence our attempt to make sense of the page. The “six + marix + morix +” text on the same line is visually suspicious to me, simply because both the marix and the morix look a lot like maria, which all matches up with the rest of the line:

That is, the line could easily, when taken as a whole, be saying something like “six + maria + maria + vix + ahia + ma+ria +”, i.e. very much less than you might at first think.

Multispectrally, the morix shows signs that its ‘o’ and ‘x’ were emended, but the rest left intact:

Of course, “six” isn’t actually a Latin word, so that too is an interpretative reading of the line. Moreover, its middle “i” is shaped completely unlike the ‘i’s in any of the Mari[ax] words, so was almost certainly emended. So: if some of the original text’s a’s were later misread (and emended) as ‘x’s, might this have originally been an abbreviation for “Sancta”, and so read more like “S[anct]a + Maria + Maria + vix + Ahia + Ma+ria +”?

And again, “vix” (= hardly, scarcely, barely, only just, with difficulty, reluctantly, etc) is perhaps not a Latin word you might expect to see in a charm or prayer: its middle “i” is shaped completely unlike the ‘i’s in any of the Mari[ax] words, so also looks like an emendation. So this too is a bit of an awkward fit.

Your thoughts, Nick?

Well, I wasn’t clear on this in 2006, and to be honest I’m not much further along in 2023. It seems to me that we’re looking at this page through the wrong kind of technical lens, because we’re not really able to answer even the simplest of questions about its codicology. Multispectral imaging was a bit of a bust for f116v, though to be fair this is exactly what a lot of the literature points out for studying pages with different ink layers (you really need Raman imaging to separate out different inks).

A different approach, which I’ve proposed for a while now, would be to map the surface of f116v to see if we can detect differences in the depth of pen indentations between different codicological layers, and then pick out the earliest layer for its meaning. And in fact, in a post on BBC Futures today, this is exactly what the Factum Foundation in Madrid has been doing with the Archiox Project for the Bodleian library.

Who knows what intrepid codicologists might find hidden in the surface of the Voynich Manuscript?

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!