AI Redates Dead Sea Scrolls

The ancient world, perpetually yielding its secrets in measured, painstaking increments, has just been nudged by the relentless march of artificial intelligence.

For decades, the Dead Sea Scrolls – those enigmatic parchment fragments unearthed from the Judean Desert caves in 1947 – have offered an unparalleled window into the earliest known texts of the Hebrew Bible, profoundly reshaping our understanding of ancient Judaism and early Christianity.

Now, a new study suggests that some of these invaluable manuscripts might be significantly older than previously surmised, a revelation born from a remarkable collaboration between traditional carbon dating and cutting-edge AI.

Imagine a time machine, not one of gleaming chrome and humming circuits, but one crafted from the very essence of human thought and belief, preserved for millennia.

That’s how Mladen Popović, lead author of the report published in PLOS One, views the Dead Sea Scrolls.

As Dean of the Faculty of Religion, Culture and Society at the University of Groningen in the Netherlands, Popović understands their profound impact.

“They completely changed the way we think about ancient Judaism and early Christianity,” he told CNN, emphasizing their role as tangible evidence of a crucial historical period.

Whether one approaches the Bible from a spiritual or purely academic perspective, its monumental influence on world history is undeniable, and the scrolls offer a unique lens through which to study its cultural evolution.

For generations, scholars have grappled with the precise age of these texts.

Almost none of the thousands of fragments bear an explicit date, leading to a general consensus that they were penned between the third century BCE and the second century CE.

But Popović’s team, employing a hybrid methodology, is challenging this long-held belief.

Their analysis, utilizing new carbon dating techniques alongside a specially trained AI program dubbed ‘Enoch,’ indicates that some manuscripts could date back to the end of the fourth century BCE.

This pushes the timeline back by as much as a century for the earliest scrolls, a significant shift in the fragile chronology of antiquity.

The journey to this new understanding was not without its complexities.

Traditional carbon dating, a cornerstone of archaeological dating, faced a peculiar hurdle: some of the manuscripts were treated with castor oil in the 1950s in a misguided attempt at preservation, a process that unfortunately interferes with accurate carbon dating.

To overcome this, Popović’s team first applied new carbon dating to a subset of the scrolls.

These results then became the training data for Enoch, the AI program.

The true test came when Enoch was presented with 135 undated manuscripts.

The AI’s estimates aligned with those of seasoned scholars a remarkable 79% of the time, a testament to its emerging capabilities.

Popović is understandably ebullient about these findings.

“With the Enoch tool we have opened a new door into the ancient world, like a time machine, that allows us to study the hands that wrote the Bible,” he declared in a statement, particularly excited by the unprecedented notion that two biblical scroll fragments now align with the presumed era of their original authors.

It’s a vision of technology not just aiding, but actively transforming, our engagement with the past.

Yet, as with any bold claim in the meticulous world of ancient scholarship, caution is the prevailing sentiment among some peers.

Christopher Rollston, a professor and chair of biblical and Near Eastern languages and civilizations at The George Washington University, offered a more tempered assessment.

While acknowledging the study’s findings as “very interesting, and presumably important,” he stopped short of deeming them “Earth-shattering.”

In an email to Live Science, Rollston pointed out that many of the article’s conclusions “dovetail with what the great palaeographers in the field, such as the late Frank Moore Cross, had already stated more than 60 years ago.”

Rollston reserved his strongest critique for Popović’s assertion that the technology allows researchers to “study the hands that wrote the Bible,” labeling it “at the very least, gross hyperbole.”

He underscored a crucial historical reality: no manuscripts of the Hebrew Bible date to the First Temple period (around 1200 to 586 BCE), when the Bible was originally composed, or even to the early parts of the Second Temple period (538 BCE to 70 CE).

For Rollston, the human element remains paramount in deciphering ancient scripts.

“Human handwriting, and all of its variations and idiosyncratic features, is a deeply human thing,” he argued.

While machines can assist in isolating script features, he concluded, “the presence of a gifted paleographer is at least as valuable as a machine-learning tool.”

Brent Seales, Alumni Professor of computer science at the University of Kentucky, though not involved in the study, echoed this measured approach.

He commended the rigor of the authors’ methodology, despite the relatively small sample size.

His advice for AI in such sensitive historical work? That it should be used with caution.

…and that “like a fine wine, it should get better over time and with more samples.”

This unfolding narrative of the Dead Sea Scrolls is more than just an updated date; it’s a compelling dialogue about the evolving nature of discovery itself.

It pits the boundless enthusiasm for technological innovation against the seasoned wisdom of traditional scholarship, highlighting the enduring tension between what machines can process and what human intuition can discern.

The scrolls, silent witnesses to millennia of human history, now stand at the forefront of a new frontier, challenging us to redefine how we unlock the secrets of the past.

The “time machine” is indeed running, but its trajectory, and the insights it truly offers, remain subjects of fascinating and ongoing debate.