To some extent it's still an interesting result: an independent validation of the original finding, and a proof of concept that this technique could make such a discovery.

I hope he collaborates with archeologists to apply these methods to their work.

IF the llm did not have the paper on it's training set. Which we do not know.

Not really. Based on a quick literature scan (it took much less than 72 hours) the technique the blog post indicates is downright primitive compared to how working archaeologists are doing it nowadays.

The main thing I see here is yet another demonstration of LLMs’ ability to boost people’s overconfidence.

> independent validation

Or the LLM had ingested the original report and thus knew what/where it was looking