At Aeon, linguistics prof Francesco Perono Cacciafoco confesses that his passion in life and work is deciphering dead languages. But, he asks, have we reached the end of the trail?

I am a glyph-breaker. I confess. Guilty as charged. A glyph-breaker who didn’t break anything, and that is quite paradoxical, because, to be a true glyph-breaker, you should have deciphered an undeciphered script, like Jean-François Champollion (the founder of Egyptology, who decoded the Ancient Egyptian hieroglyphs), Henry Rawlinson (who gave us the key to cuneiform) or Michael Ventris (who deciphered Linear B). Well, I didn’t. But I tried. I still try, in a way. And, in our times of devolution, that probably qualifies a guy to be called a glyph-breaker. The age of the great decipherments is, in all likelihood, over. What remains: a considerable amount of poorly documented, extremely elusive writing systems and ‘inscribed relics’, like Linear A, the Indus Valley Script, Rongorongo, and the Singapore Stone. Puzzles. Possibly unsolvable. Headache-generators. Nasty stuff.

“The lonely life of a glyph-breaker,” April 7, 2025

Like many decoders of these ancient scripts, he uses AI for assistance. His goal is decoding the so-far-undeciphered ancient language of Crete, Minoan Linear A. But he is realistic about what AI can do:

Technology cannot replace human ingenuity and cannot lead automatically to the decipherment of an undeciphered script. But it can save a lot of work and pain to scholars. My team developed a Python program that feeds a computer we called ‘The Machine’ that can develop, in a reasonable amount of time, an exhaustive cryptanalytic brute force attack on the Linear A signs. “Glyph-breaker,”

Why does it matter?

That Cacciafoco can readily answer:

Once a writing system is finally deciphered, a new world opens before our eyes. Before that, we knew a civilisation that used a script we weren’t able to read only through its material culture, archaeological findings and remains or external historical sources. After we’re able to read the writings of that civilisation, a whole new treasure trove of information is readily available to us. Deciphering languages is, therefore, not only the archaeology of writing, but the only discipline that allows us to discover ancient peoples through their own words, by reading the documents they left behind.

Indeed. He zeroes in on the reason we see documentaries and read books about the ancient Egyptians: Deciphering the hieroglyphs meant that “the Egyptian civilisation started to talk directly to us. Its depiction of itself included not just its macro-history (the dynasties, the pharaohs, Alexander the Great, the Romans), but also the daily life of ordinary people and all the secrets that only written texts can unveil.”

Wish him luck. Deciphered writing is one of the few things that can build bridges for our thoughts across time.

You may also wish to read: Does AI challenge Biblical archeology? Sadly, many surviving documents are so damaged that they cannot be read using traditional methods. The more scrolls are deciphered using new AI methods, the more archeologists will have to study and write about.

Can AI help us decipher lost languages? That depends mainly on the reasons we haven’t yet deciphered ancient texts in the past. AI can speed up translation of ancient documents where only a few scholars know the language. Whether it can help with mysterious unknown languages like Minoan A is another question.