this post was submitted on 18 Aug 2023
5 points (100.0% liked)

Asklemmy

43404 readers
1761 users here now

A loosely moderated place to ask open-ended questions

Search asklemmy ๐Ÿ”

If your post meets the following criteria, it's welcome here!

  1. Open-ended question
  2. Not offensive: at this point, we do not have the bandwidth to moderate overtly political discussions. Assume best intent and be excellent to each other.
  3. Not regarding using or support for Lemmy: context, see the list of support communities and tools for finding communities below
  4. Not ad nauseam inducing: please make sure it is a question that would be new to most members
  5. An actual topic of discussion

Looking for support?

Looking for a community?

~Icon~ ~by~ ~@Double_A@discuss.tchncs.de~

founded 5 years ago
MODERATORS
 

What if we never found the Rosetta Stone and could not read ancient Egyptian hieroglyphics. Could computers or AI decipher them today?

top 7 comments
sorted by: hot top controversial new old
[โ€“] CanadaPlus@lemmy.sdf.org 1 points 1 year ago (1 children)

Probably not. We can algorithmically show if something is likely to be writing, but actually understanding it is a very complicated process that involves a lot of social sciences inferences. An LLM using chain or tree of thought would probably be your best shot.

I think if you're trying to model completely agnostically on every language possible translating entire words and existing known pictograms to what they mean. Then there might be a slight chance that kind of deciphering part of it. Just because humans usually come back to similar symbols and maybe it can pick up on something that we can't. But it would be a long shot to be sure

[โ€“] shartworx@sh.itjust.works 1 points 1 year ago (1 children)

Here's what ChatGPT 3.5 says:

The Rosetta Stone played a crucial role in deciphering Egyptian hieroglyphics because it provided a key to understanding the script by presenting the same text in three different scripts: Ancient Greek, Egyptian hieroglyphics, and demotic (a simplified script used for everyday purposes). This allowed scholars to correlate the known Greek text with the Egyptian texts and begin to decipher the hieroglyphics.

A GPT-based AI, while powerful in many ways, would likely face significant challenges in deciphering Egyptian hieroglyphics without access to something akin to the Rosetta Stone. Here's why:

  1. Lack of Direct Contextual Data: GPT models learn from a vast amount of text data, but the historical and contextual gap between modern languages and ancient Egyptian hieroglyphics is enormous. GPT models might not have enough direct or relevant data to bridge this gap.

  2. Limited Multilingualism: GPT models, including their previous versions like GPT-3.5, do not inherently "know" multiple languages the way humans do. They have learned statistical patterns in text, which enables them to generate text in multiple languages but doesn't guarantee deep understanding or translation of highly specialized languages like hieroglyphics.

  3. Lack of Connection to the Rosetta Stone Context: GPT models lack the ability to access external sources or historical events, which is what made the Rosetta Stone so invaluable in deciphering hieroglyphics. Without access to that kind of contextual information, it would be difficult for the model to make the necessary connections.

  4. Complex Symbolic Nature: Egyptian hieroglyphics are not a straightforward language like those GPT models are trained on. Hieroglyphics use a combination of ideograms, phonograms, and determinatives to convey meaning. The complexity of hieroglyphics goes beyond the syntax and structure of modern languages, making it a unique challenge.

In summary, while a GPT-based AI could perform some basic statistical analyses on hieroglyphics to identify patterns, it's unlikely to decipher the script in a comprehensive and accurate way without a Rosetta Stone-like source that provides a bridge between the ancient script and a known language. Hieroglyphics represent a highly specialized domain that would require deep contextual understanding, which GPT models might struggle to achieve given their current capabilities.

[โ€“] CanadaPlus@lemmy.sdf.org 2 points 1 year ago

Good job ChatGPT! The only correction I'd make is that logographic writing is still used in languages like Chinese.

[โ€“] shinigamiookamiryuu@lemm.ee 0 points 1 year ago (2 children)

Yes, it has already deciphered some languages and is even being used on animals now.

[โ€“] CanadaPlus@lemmy.sdf.org 2 points 1 year ago

If I read correctly, they taught it to decipher cuneiform using the known translations. It didn't "crack it" itself.

I really hope they can use this to decipher the Harappan script. That's like the holy grail of lost languages for me. I want to know so badly!