[ih] Comments re the packet radio discussion

Steve Crocker steve at shinkuro.com
Wed Apr 22 17:24:45 PDT 2026


The Incas also had a remarkable network.  Roads leading out from Cusco,
with messages carried verbally by runners.  Iwas exposed to this history
only briefly, so I can't duplicate Jack's recounting of the Roman network.

Steve


On Wed, Apr 22, 2026 at 8:14 PM Jack Haverty <jack at 3kitty.org> wrote:

> Hi Len,
>
> Yes, I started with the call K3FIV, switched to WA1WGI when I moved to
> Massachusetts, and then retrieved K3FIV as my call after the FCC stopped
> enforcing the geographic rules.  Back in high school, there was also a
> "surplus shop" in the 1960s down in the bowels of Philadelphia where I
> used to find all sorts of gear that provided lots of components for use
> in ham stations.  Old WWII equipment was still easily available and
> cheap.   Like you, I've always been fascinated by the magic of action at
> a distance.
>
> Ham radio was where I first learned networking issues and concepts.  But
> a few years later, still in high school, I had a teacher who for some
> reason was passionate about the history of the Roman Empire.   I
> accidentally learned even more about networking in his classes.
>
> It turns out that the Roman Empire also depended on its own Internet to
> communicate with, and especially to manage, its Empire which covered
> much of Europe and reached into parts of Asia and Africa.  Computers
> didn't exist, so their Internet was implemented by human processors and
> a web of interconnections composed of the Roman roads and ships (e.g.,
> "triremes") for "circuits" across the Mediterranean.   The standard
> catchphrase to describe that era is "All roads lead to Rome", but a more
> accurate one would be "Roman roads lead to everywhere in the Empire."
>
> I learned a lot in those classes about how the Roman Internet worked.
> It relied on Scribes, to create "papyrus datagrams" and couriers, who
> provided the means to transmit the papyrus datagrams.  The roads were
> the "circuits" transporting "datagrams", on papyrus "packets" in the
> runners packs.  Some parts of their Internet were terrestrial, with
> Couriers literally running on the roads.  Others were shipboard and
> mobile, perhaps with the Couriers as rowers.  No radio networks though....
>
> Over several centuries, the Romans developed and evolved algorithms and
> protocols.  Obviously they required routing mechanisms, but also used
> other technology.  For example, very important messages would be sent
> using Scribes to make copies of datagrams, and send couriers with each
> copy to the destination, using alternate routes. Particularly "lossy"
> circuits (e.g., where pirates roamed) could motivate using similar
> techniques to improve the probability of a successful transmission.
>   Latency was a problem, with transit times measured in days or weeks,
> but sending multiple messages by "diversity routing" deemed to mitigate
> the need for error control or retransmission protocols in such latency
> conditions..
>
> Security was an issue of course.  But a papyrus scroll could easily be
> ripped into strips, and each strip sent by a different courier, even
> over different routes.  They didn't call it "fragmentation" and
> "reassembly" but that's pretty much what happened and it provided
> security too.  Encryption using code words might have been used too.  Or
> both if needed.  Scribes and Couriers were slaves, easily available and
> cheap.
>
> Sometimes datagrams had to go to multiple destinations.  When the Roman
> Senate declared war on Carthage (in Africa) some Senator In Rome shouted
> "Carthago delenda est!" (Carthage must be destroyed!) That message had
> to get to all the scattered legions of the Roman Army to inform them of
> a declaration of war.  I can imagine that a few papyrus datagrams
> travelled across the Mediterranean to ports in Africa, were then copied
> by Scribes, and a copy sent directly by lots of couriers in parallel to
> deliver it to each military unit in Africa.   They didn't call it
> "multicast" but it addressed the same need.
>
> FYI to anyone interested, I also recommend the book "The Victorian
> Internet" (see https://en.wikipedia.org/wiki/The_Victorian_Internet ).
> I didn't read this until recently, but it is another example discussing
> an older Internet of the pre-computer times.  The book describes the
> emergence of Morse Code and the whole system of Telegraphy that
> developed in the 19th century.  The description of the "social media"
> that developed among the widely scattered population of operators was
> interesting too.  When traffic loads were light, operators could easily
> talk to each other, not just exchanging "routing updates".
>
> There's a lot of detail included about the impact that the "Victorian
> Internet" had on society, business, and culture of that era.  IMHO,
> we're right now going through a similar historical transition with our
> own Internet and global societies, but the book describing that
> experience can't be written quite yet.
>
> I suspect the Egyptians or Greeks might also have an Internet but I
> didn't have a teacher who was into their history.  The Romans must have
> learned about Internets from someone.  Maybe the Sumerians....
>
> Humans have been using Internets, and developing appropriate algorithms
> and protocols to implement them using the technology of the day, for
> quite a long time.....
>
> /Jack Haverty
>
> On 4/21/26 20:09, Leonard Kleinrock wrote:
> > Jack, your experiment in high school with Ham Radio and Morse code and
> its eventual use to help ARPA out is delicious.  Do you still have your ham
> radio call sign? I had a less interesting but somewhat related experience
> as a child when I built operating radios out of cannibalized broken radios
> that were thrown out by folks in my New York tenement apartment building.
> But, son of a gun, in spite of the fact that I learned Morse Code, I
> couldn’t afford to become a Ham operator since the “rig” itself was far too
> expensive. But the excitement of action at a distance that radio provides
> was fascinating magic and seduced me for life.
> > Len
> > Sent from my iPhone
> >
> >> On Apr 21, 2026, at 7:41 PM, Steve Crocker via Internet-history <
> internet-history at elists.isoc.org> wrote:
> >>
> >> Great story!
> >>
> >> Sent from my iPhone
> >>
> >>> On Apr 21, 2026, at 10:14 PM, Jack Haverty via Internet-history <
> internet-history at elists.isoc.org> wrote:
> >>>
> >>> Glad to see that AI is on the problem!
> >>>
> >>> My first encounter with network technology involved AI.  I had a lot
> to learn about networking.  Somewhat long story...sorry, just hit delete
> now if you aren't interested.
> >>>
> >>> It started in 1963.  In high school, I was interested in STEM (acronym
> not yet in existence though), had joined the school's Radio Club, gotten a
> amateur radio ("ham") license, and somehow gotten involved in something (in
> the US) called the National Traffic System (NTS - that acronym did exist).
> >>>
> >>> NTS was a network.  Actually an Internet.   Actually a
> multi-technology Internet of interconnected networks.  It had been evolving
> since shortly after World War II.  Packets (think telegrams or emails) were
> transported around the world.  There were LANs covering cities, Regional
> nets over the US, and gateways to nets covering other parts of the world.
> Even a TransContinentalCorps (TCC) that acted as a WAN.
> >>>
> >>> I learned about all sorts of the technical mechanisms that operated
> inside the network: routing, flow control, addresses, error control,
> protocols for retransmissions, compression techniques, etc.
> >>>
> >>> NTS typically carried messages such as Birthday Greetings, e.g., from
> a soldier stationed in Guantanamo Bay (address: "GITMO") to a family member
> back home somewhere in the US.  Although most of the distance was covered
> by radio, using Morse Code, the final link might use a different "LAN",
> e.g., a telephone call or even simply driving to the house and delivering a
> piece of paper.  NTS still operates today.  More details at
> https://en.wikipedia.org/wiki/National_Traffic_System if you're curious.
> >>>
> >>> When I was in Lick's orbit at MIT, that experience made it easy for me
> to understand the ARPANET.  Later also the Internet.   Techniques were
> different but the problems remained the same.
> >>>
> >>> At one point circa 1975, ARPA asked for our help with a critical DoD
> need.  They wanted computers to be able decode hand-sent Morse code.  No
> one ever explained exactly why to us tech grunts, but we knew Morse was
> being used by both the good and bad guys.  The AI technology of the day was
> "Expert Systems".   We were tasked to use whatever we thought would help
> solve the problem.
> >>>
> >>> That started a project which lasted several years, and produced a
> system which did about as well, possibly even better, than a human
> operator.  From my high school experience, I acted as the "Expert", and we
> had a series of staff and student projects to make the PDP-10 do the same
> things I had learned to do while participating in the radio network.  ARPA
> was happy.  DoD was happy.  No ham operator could afford the millions of
> dollars to have their own PDP-10 system, but the government didn't have
> that constraint.
> >>>
> >>> The project even appeared in a 1990 Mitre report I think of as a
> compendium of "ARPA's Greatest Hits".  See Chapter 22 of
> https://apps.dtic.mil/sti/tr/pdf/ADA239925.pdf  (FYI, ARPANET is Chapter
> 20 of same report).
> >>>
> >>> The reason I mention this is because Gemini's interpretation reminded
> me of the behavior we noted in that AI system -- in 1975. The radio
> environment was pretty nasty, with conditions such as interference or
> lightning strikes randomly causing "dropped packets", which the network had
> to mitigate.  The software we built had parameters which we could change to
> modify how confident it had to be before issuing a translation of the
> "Morse" it was hearing. It was in effect a "knob" that you could use to
> tell the system how hard to work to do its job.
> >>>
> >>> One day, just for the hell of it, we set the confidence knob as low as
> it could go.  Then we tuned the radio to a frequency with no one
> transmitting at all, just atmospheric noise.
> >>>
> >>> The system tried real hard.  The processor was no doubt overheating.
> The memory cores were melting.  But it produced words.  It created
> sentences.  It created paragraphs.  It described things and the content
> actually made sense.  All of it was nonsense of course, pure gibberish.
> >>>
> >>> Unless... perhaps we were actually listening to some extraterrestrial
> communications?  We should have informed SETI.  Klingonese or Cardassian --
> didn't matter, it is still proof - "they do exist!"
> >>>
> >>> Today's AI is apparently even more creative in interpreting
> gibberish.  It even explains how it's reaching its conclusions!
> >>>
> >>> /Jack
> >>>
> >>>>> On 4/21/26 13:39, vinton cerf wrote:
> >>>> gemini:
> >>>>
> >>>> It looks like you’ve found the "right-side up" version of the text
> you shared earlier! Seeing it this way makes the patterns much clearer,
> though it’s still definitely dancing on the edge of "uncanny valley"
> English.
> >>>>
> >>>> This isn't a standard language; it’s a form of *pseudo-English* or
> *Asemic writing*. It’s designed to /look/ like a coherent paragraph to your
> brain at a distance, but when you zoom in, the words dissolve.
> >>>>
> >>>>
> ------------------------------------------------------------------------
> >>>>
> >>>>
> >>>>      The Linguistic Breakdown
> >>>>
> >>>> While it’s mostly gibberish, we can "reverse engineer" the intended
> words based on the letter structures. It feels like a corrupted digital
> file or a transcript from an AI that’s having a minor stroke.
> >>>>
> >>>> *Key "Deciphered" Fragments:*
> >>>>
> >>>> *
> >>>>
> >>>>    *"medete ont to emoe ‘entmaxe o bear ed outs"*
> >>>>
> >>>>     o
> >>>>
> >>>>        /Translation:/ "Meditate on to come, examine to bear the outs."
> >>>>
> >>>> *
> >>>>
> >>>>    *"eae onkwsxs oF beats nood nat Iebow"*
> >>>>
> >>>>     o
> >>>>
> >>>>        /Translation:/ "Are knows of beats down that I bow."
> >>>>
> >>>> *
> >>>>
> >>>>    *"edt of paatectire ant Moold"*
> >>>>
> >>>>     o
> >>>>
> >>>>        /Translation:/ "The architecture and mold" (or "world").
> >>>>
> >>>> *
> >>>>
> >>>>    *"guivkscer his note a buat cence?"*
> >>>>
> >>>>     o
> >>>>
> >>>>        /Translation:/ "Receiver his note a [about?] sense?"
> >>>>
> >>>>
> ------------------------------------------------------------------------
> >>>>
> >>>>
> >>>>      What is this, exactly?
> >>>>
> >>>> Since you aren't sure where it came from, here are the three most
> likely suspects:
> >>>>
> >>>> 1.
> >>>>
> >>>>    *A "Markov Chain" Generator:* This is a classic result of an
> >>>>    algorithm being fed a lot of old literature (like Poe or
> >>>>    Lovecraft) and trying to predict the next letter. It gets the
> >>>>    "rhythm" of the words right, but the spelling fails.
> >>>>
> >>>> 2.
> >>>>
> >>>>    *Optical Character Recognition (OCR) Gore:* If someone scanned a
> >>>>    very old, physically damaged book using cheap software, the
> >>>>    computer might have guessed the letters incorrectly, resulting in
> >>>>    this "alphabet soup."
> >>>>
> >>>> 3.
> >>>>
> >>>>    *Weirdcore / Digital Art:* There is a massive online subculture
> >>>>    that creates "cryptic artifacts"—text that looks haunted or
> >>>>    forbidden—just to spark curiosity.
> >>>>
> >>>>
> >>>>      My "Best Guess" at the Meaning
> >>>>
> >>>> If I had to summarize the "vibe," it reads like a *distorted manual
> for a ritual or a meditation guide.* It uses words like /meditate, examine,
> architecture, slumberous,/ and /note./ It’s trying to tell you to look at
> something ("examine to bear the outs"), but the "signal" is breaking up.
> >>>>
> >>>>    *Technical Note:* Notice how it uses "u" and "n" or "p" and "b"
> >>>>    interchangeably? That’s a hallmark of text that was meant to be
> >>>>    read upside down (the "Flip Text" from before). It was likely
> >>>>    written specifically to be readable—albeit weirdly—from both
> >>>>    directions.
> >>>>
> >>>> *Where did you encounter this?* Was it in a text file, a hidden
> comment in code, or maybe a strange social media "bot" account? Knowing the
> medium might help me figure out if there's a hidden key to the gibberish.
> >>>>
> >>>>
> >>>>> On Tue, Apr 21, 2026 at 4:29 PM Carsten Bormann via Internet-history
> <internet-history at elists.isoc.org> wrote:
> >>>>    Hmm, I really wanted to get-bunter-ebay already, and I could
> >>>>    definitely use a few Denknuxe (*).
> >>>>
> >>>>    So I asked deepseek, and it suggested this might have been scanned
> >>>>    upside down (or maybe as ink leaked through the page?).
> >>>>    It couldn’t really help any further though except suggesting a
> >>>>    service like https://www.upsidedowntext.com/, which gets me (not
> >>>>    quite what I was looking for):
> >>>>
> >>>>    ɯǝpǝʇǝ ouʇ ʇo ǝɯoǝ ‘ǝuʇɯɐxǝ o qǝɐɹ ǝp onʇs
> >>>>    ǝɐǝ ouʞʍsxs oℲ qǝɐʇs uoop uɐʇ Iǝqoʍ
> >>>>    ┴p ‘ ǝpʇ qǝǝ ɐɯǝ ʇɐʌǝ uǝɹuɐbǝʇ Ԁ∀ƃɥ¿ ˥ᴉǝs
> >>>>    | ɐlqɐɥǝɹǝs ɐɐpʇo >ɐǝʞ ┴onɐɹs slǝɐᴉuᴉɐs ǝnɹos˙ poʇᴉʇʎ uq(
> >>>>    ǝǝʇ ʇo ʇooʇʇǝ ǝp¿ ‘s)ɐoʇzɐzɐ ǝpʇ oɟ dɐɐʇǝɔʇᴉɹǝ ɐuʇ Woolp «
> >>>>    ʍɥǝ oʇ pǝuʞunxǝ פǝsp ouᴉx ɐǝp ǝɟouʇǝɹɹs¿ opʎ sǝ ǝʌoʇʇǝp |
> >>>>    ǝɐǝ ʍǝǝ ɥǝuʇɐƃ( ƃǝʇqnuʇǝɹǝqɐʎ ǝps ┴Hɹǝɯǝlƃbns' oʇ qoʍ ƃɐʇǝp oʇɐ
> ƃᴉɐo
> >>>>    ‾ ʇoɐʇoʍƃ ɟǝsɔoɯʇsǝƃzǝ ǝpʇ ʇopʎ˙ o8˙ ǝɯoɹǝxǝ oʇɥɐ ʇǝxᴉɐb ʇǝ )ǝp
> >>>>    Iʍɐs’: ɟǝuʇᴉʎ ɾ
> >>>>    op Sᴉʞʍ ʇɐls sonɹʇɐsʇ ǝqɐɹobɹoǝɐʇ ɯǝu ɯsʇoʎǝ ƃnᴉʌʞsɔǝɹ ɥᴉs uoʇǝ ɐ
> >>>>    qnɐʇ ɔǝuɔǝ¿
> >>>>
> >>>>    Maybe some other AI can help here…
> >>>>    Need to find a student.
> >>>>
> >>>>    Grüße, Carsten
> >>>>
> >>>>    (*) The first sentence of my message is easier to understand if
> >>>>    you speak German.
> >>>>
> >>>>> On 2026-04-21, at 22:10, Jack Haverty via Internet-history
> >>>>    <internet-history at elists.isoc.org> wrote:
> >>>>>>    medete ont to emoe ‘entmaxe o bear ed outs
> >>>>>>    eae onkwsxs oF beats nood nat Iebow
> >>>>>>    TD ‘ edt bee ame tave nernaqet PAgh? Lies
> >>>>>>    | albaheres aadto <aek TouaRs sleainias euros. dotity nb)
> >>>>>>    eet to tootte ed? ‘s(aotzaza edt of paatectire ant Moold «
> >>>>>>    whe ot Denknuxe Gesd onix aed efonterrs? ody se evotted |
> >>>>>>    eae wee hentag) getbunterebay eds THremelgqus, ot bow gated
> >>>>    ota giao
> >>>>>>    _ toatowg fescomtsegze edt tody. o8. emorexe otha texiaq te
> >>>>    (ed Iwas’: fentiy j
> >>>>>>    od Sikw tals sourtast ebaroqroeat men mstoye guivkscer his
> >>>>    note a buat cence?
> >>>>>>
> >>>>>>    I guess I'm still not allowed to read this PRTN....
> >>>>>>
> >>>>>>    Medete ont to you too!
> >>>>>>
> >>>>>>    /Jack
> >>>>    --     Internet-history mailing list
> >>>>    Internet-history at elists.isoc.org
> >>>>    https://elists.isoc.org/mailman/listinfo/internet-history
> >>>>    -
> >>>>    Unsubscribe:
> >>>>
> https://app.smartsheet.com/b/form/9b6ef0621638436ab0a9b23cb0668b0b?The%20list%20to%20be%20unsubscribed%20from=Internet-history
> >>>>
> >>> --
> >>> Internet-history mailing list
> >>> Internet-history at elists.isoc.org
> >>> https://elists.isoc.org/mailman/listinfo/internet-history
> >>> -
> >>> Unsubscribe:
> https://app.smartsheet.com/b/form/9b6ef0621638436ab0a9b23cb0668b0b?The%20list%20to%20be%20unsubscribed%20from=Internet-history
> >>> <OpenPGP_signature.asc>
> >> --
> >> Internet-history mailing list
> >> Internet-history at elists.isoc.org
> >> https://elists.isoc.org/mailman/listinfo/internet-history
> >> -
> >> Unsubscribe:
> https://app.smartsheet.com/b/form/9b6ef0621638436ab0a9b23cb0668b0b?The%20list%20to%20be%20unsubscribed%20from=Internet-history
>
>

-- 
Sent by a Verified

sender


More information about the Internet-history mailing list