Dead Kings with AI

Dead Kings Revived Via AI

When it comes to dead kings and lost empires, it’s very easy to circle back to England—the land of old, where such kings as King Henry the Eighth and the legend of King Arthur lived, where books like Game of Thrones have been adapted to preserve history by what we could find, limited by resources and human functionality.

But what if I was to tell you... there was a whole kingdom just as prevalent, filled with kings, legends of old, usurpers, taxes, and double-crossing? Being uncovered by AI at this very moment, in the historical documents preserved by South Korea. It is the Joseon Dynasty, which ruled Korea with kings for over five hundred years.

For decades, scholars devoted their lives to uncovering the secrets of these forgotten kings. Now, anyone who has been knows how easy it is to fall in love with the culture, the cuisine, and the people—but under all that lies a rich past, fought with medieval battles and a longing for peace.

AI Preserving History Through Language

Now, AI is doing what historians once did—preserving the record—by using the latest AI technology built on the powerful learning model known as Transformer architecture.

AI researchers and engineers have begun developing a Multilingual Neural Machine Translation system, otherwise known as MNMT, to decipher ancient texts. These systems train on three languages at once: the original ancient script (Hanja), Old Korean, and modern tongues. When full translations don’t exist, AI fills in the gaps—drawing on pattern recognition across massive datasets, from Chinese character structures to Korean syntax.

What would take scholars decades is being decoded in months. The ministers and scribes dedicated their lives to writing everything down, including one such story found through research: King Taejong fell off his horse and, embarrassed, pleaded with the historian not to write it down. As clinical proof of their invaluable insight, the minister-historian wrote The Accident and The King’s Plea—holding tight to the integrity of unknown history.

AI Decoding What Scholars Couldn’t

But now, with machines, we are decoding texts that, for decades, scholars spent their lives chipping away at—only to be met with impossible obstacles: overwhelming cost, decades-long timelines, and the sheer weight of unreadable history. The decoding AI It’s not perfect—but it’s fast, relentless, and self-teaching. AI is learning to speak in dead languages.

And in doing so, it’s rebirthing South Korea’s ancient past—giving us a once-in-a-lifetime insight into dead kings. But the Joseon Dynasty isn’t the only ancient voice AI is helping us hear.

In the deserts of Iraq and Syria, AI tools are being turned toward Akkadian cuneiform tablets—some of the oldest written records in human history. For centuries, their wedge-shaped script sat undeciphered. But now, with deep learning models trained on ancient Semitic languages, AI is beginning to read them fluently—revealing stories of gods, kings, and commoners we thought were gone forever.

Some of the Akkadian tablets tell of kings who weren’t just rulers—they were seen as divine. Chosen by gods like Marduk, crowned as the living or decades — for years—these tablets were damaged and incomplete. Just little pieces, unmatched symbols, whispers of ceremony with nobody to hold them or any accuracy. Only in myth and belief did we know of one of the first true empires. The cuneiform they used is next to impossible for researchers and scholars alike—trying to decipher a dead Semitic language that shifts form and meaning depending on the era, location, and whoever held the stylus to write it.

But now, using the latest deep learning machines built on this ancient code—AI systems like CDLI-100M—researchers are feeding in over 100,000 annotated cuneiform lines, plus linguistic data spanning from Hebrew, Arabic, and other Semitic tongues, to help predict missing lines, rebuild damaged texts, and spot the divine language buried in their patterns.

And bringing them back to be spoken in modern life. They’re putting together forgotten ceremonial phrases such as:

“He walked under the gaze of Marduk,”
“Crowned in the shadow of the heavens,”
“The god’s echo in mortal form.”
And bringing them back to be spoken in modern life. So what’s the takeaway?

That all kings fall off horses. That scribes don’t always listen.

That once, we spoke to gods in wedges of clay and performed vast ceremonies to be remembered.

And now, thanks to AI—to deep learning machines trained on silence and dust—we’re beginning to uncover it all.

And the truth is... we’re only at the beginning.

Don't miss out on the latest news!
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

People also read

AI and the Future of the Museum Experience

AI is entering museums in practical ways: systems that register visitor behaviour, adjust content, and reorganize the experience in real time. This article looks at how these tools change the museum visit and how attention, interaction, and personalization are evolving.
Ludovica Russo
Ludovica Russo
November 18, 2025
5
min read
Generative AI

Teaching Machines Empathy: The Human Lessons in War Literature

When war reduces people to numbers, literature restores their faces. This essay reflects on how novels such as The Nightingale, Gone with the Wind, and Half of a Yellow Sun preserve empathy in times when conflict erodes it. Moving from the moral weight of storytelling to the rise of artificial intelligence, it asks whether machines trained on data can ever understand the human cost of suffering. In an age of algorithmic precision, it’s a reminder that intelligence without empathy risks repeating the same blindness that war reveals.
Warda Khan
Warda Khan
November 4, 2025
7
min read
Generative AI
Historical Events
History

When AI ‘Fictions’ Redirect History: Generative Models, Historiography and Misinformation

This article investigates the epistemic risks generative AI poses for historical research and education. It shows how large language models routinely produce hallucinatory outputs—fabricated references, misattributed quotations, and conflated events—presented with authoritative confidence, potentially misleading scholars and the public. By analyzing these dangers alongside AI’s affordances, it underscores the need for historians to exercise critical verification, methodological caution, and transparency when using AI in historiography and pedagogy.
Eleni Paipeti
Eleni Paipeti
October 29, 2025
7
min read
Generative AI
AI Bias
Ethics

Contribute to Historica's blog!

Learn guidelines, requirements, and join our history-loving community.

Become an author

FAQs

How can I contribute to or collaborate with the Historica project?
If you're interested in contributing to or collaborating with Historica, you can use the contact form on the Historica website to express your interest and detail how you would like to be involved. The Historica team will then be able to guide you through the process.
What role does Historica play in the promotion of culture?
Historica acts as a platform for promoting cultural objects and events by local communities. It presents these in great detail, from previously inaccessible perspectives, and in fresh contexts.
How does Historica support educational endeavors?
Historica serves as a powerful tool for research and education. It can be used in school curricula, scientific projects, educational software development, and the organization of educational events.
What benefits does Historica offer to local cultural entities and events?
Historica provides a global platform for local communities and cultural events to display their cultural artifacts and historical events. It offers detailed presentations from unique perspectives and in fresh contexts.
Can you give a brief overview of Historica?
Historica is an initiative that uses artificial intelligence to build a digital map of human history. It combines different data types to portray the progression of civilization from its inception to the present day.
What is the meaning of Historica's principles?
The principles of Historica represent its methodological, organizational, and technological foundations: Methodological principle of interdisciplinarity: This principle involves integrating knowledge from various fields to provide a comprehensive and scientifically grounded view of history. Organizational principle of decentralization: This principle encourages open collaboration from a global community, allowing everyone to contribute to the digital depiction of human history. Technological principle of reliance on AI: This principle focuses on extensively using AI to handle large data sets, reconcile different scientific domains, and continuously enrich the historical model.
Who are the intended users of Historica?
Historica is beneficial to a diverse range of users. In academia, it's valuable for educators, students, and policymakers. Culturally, it aids workers in museums, heritage conservation, tourism, and cultural event organization. For recreational purposes, it serves gamers, history enthusiasts, authors, and participants in historical reenactments.
How does Historica use artificial intelligence?
Historica uses AI to process and manage vast amounts of data from various scientific fields. This technology allows for the constant addition of new facts to the historical model and aids in resolving disagreements and contradictions in interpretation across different scientific fields.
Can anyone participate in the Historica project?
Yes, Historica encourages wide-ranging collaboration. Scholars, researchers, AI specialists, bloggers and all history enthusiasts are all welcome to contribute to the project.