AI helped decipher a philosopher’s musings about ‘pleasure’ after they were buried by Vesuvius’ eruption 2,000 years ago

  • An ancient Greek philosopher’s musings about “pleasure” have been rediscovered in an ancient passage.
  • The passage is from a scroll that was buried after Mount Vesuvius erupted 2,000 years ago.
  • A team of students deciphered the passage with AI technology, winning them $700,000 in prize money.

Thanks for signing up!

Access your favorite topics in a personalized feed while you’re on the go.

Armed with AI, a trio of young students have accomplished in a single year what scientists couldn’t in 272 years.

Luke Farritor, a student at the University of Nebraska-Lincoln and former SpaceX intern, Youssef Nader, an Egyptian PhD student in Berlin, and Julian Schilliger, a Swiss robotics student in Zurich, deciphered text on a 2,000-year-old papyrus scroll, winning them $700,000 of prize money in the process.

The scroll is just one of hundreds that were first excavated in 1752. Named the Herculaneum Scrolls, after the city they were found in, the collection is the only library left from the ancient world. But their secrets remained unknown for the last 272 years.

The University of Kentucky team scanned the Herculaneum scroll and took X-ray images of the inside.

No one could decipher them because they’d been burned and buried when Mount Vesuvius erupted about 2,000 years ago, leaving them charred and far too delicate to unroll. In fact, previous efforts to read them yielded limited success and damaged some of the scrolls.

Enter AI technology. The brilliant student trio used a combination of AI and 3D mapping to decipher letter shapes in a small section of the scroll. Their efforts were part of a competition called the Vesuvius Challenge, a contest that launched in 2023 offering citizen scientists $1 million in prizes to whomever could transcribe part of the scroll’s text.

What the scroll said

The Vesuvius Challenge’s grand-prize winning image of several columns of text from a papyrus sheet created by Youssef Nader, Luke Farritor, and Julian Schilliger.
The University of Kentucky via the Vesuvius Challenge

The newly translated passages are thought to originate from the Epicurean philosopher Philodemus and contain his thoughts on music and food.

“The Epicureans had much to say about pleasure and pain, and even in this text, there is a discussion of how abundance and scarcity can affect our pleasure,” Brent Seales, a computer science professor at the University of Kentucky who took X-ray CT scans of the ancient scrolls in 2009, said in a statement.

On Monday, Nat Friedman, a tech executive and former CEO of GitHub who became obsessed with the scrolls during the 2020 Covid lockdown and helped fund the challenge excitedly posted on X (formerly Twitter): “Today we are overjoyed to announce that our crazy project has succeeded. After 2,000 years, we can finally read the scrolls.”

First-prize winner for the second time

Farritor had already won first place in the Vesuvius Challenge’s “First Letters Prize,” winning him $40,000 last year.

He, along with second-place winner Nader, used AI to become the first to read a single word from the scroll. The word was translated from Greek to mean “purple dye” or “clothes of purple.”

The first word deciphered from the scroll was translated to mean “purple dye.”
Vesuvius Challenge, via University of Kentucky

Several months later, Nader and Farritor, in collaboration with Schilliger had translated entire passages.

They went above and beyond the contest’s stipulated four columns of text and read an additional 11 partial columns. In total, they transcribed hundreds of words, earning them the grand prize of $700,000.

However, the students couldn’t have done it without the dedicated work from Seales and his team of researchers.

Seales’ used the CT scans to create the software for virtually unwrapping the scrolls in the first place.

Seth Parker and Brent Seales of the Digital Restoration Initiative project scan a replica of the Herculaneum scroll.
UK Photo

He and a team of researchers then flattened out the images so they weren’t on top of each other like the layers of an onion, and then used machine learning to identify areas with ink.

Currently, researchers have only unrolled and deciphered about 5% of a single scroll. Scholars are hoping to find lost treasures from Aristotle or Homer in the other 280 papyri, Nature reported.

Read More

Beatrice Nolan