Translating Akkadian clay tablets with ChatGPT?

Also, it’s interesting that in 2023, we can reasonably definitively answer that question for any definition of “dream”.

Moving back to when I first saw this post, I immediately gravitated towards checking the "translation" and so neglected to read anything else written. Now that I've lovingly wasted my time transcribing and translating from the supplied transliteration before checking Leichty [0], I can move on to wasting my time with the other issues.

The initial complaint about a "Karen" is obnoxious and unhelpful. You can always _write down_ the id number or title of an object in a museum if you have a specific interest. If the tablet one is interested in is Biblically relevant, then it is almost certainly referenced in literature (which you can take a shortcut to find said literature if you have that number you wrote down). All you have to do is some reading and/or contacting of relevant scholars. Tablets with references to Biblical events and persons are often exceptionally well documented due to Biblical scholarship's smothering embrace of Assyriology. If you think there might be multiple copies of this tablet, then you could ask Hobby Lobby's if they have a copy in their collection they obtained by funding ISIS. I'm sure they would love to talk about it.

Moving away from museum etiquette, there are some other issues. Searching through the CDLI requires some effort. It is a tool, not a search engine with results ranked for relevance and ad revenue. Knowing the language and the processes of transliteration, transcription, and translation will help. Spellings can vary within dialects and search will not conjugate or magically find alternative cases for you. The transliterations on the CDLI are less than perfect so don't think you can just train some LLM to do this for you (There is a lot of bad data. Feel free to make some more bad data by doing some transliterating yourself with the provided low dpi images. Transliterating without both the tablet and a movable light source in front of you can border on impossible. You might make a transliteration, but it will be bad if you lack the will spend weeks staring at a photograph.). I found at least 25 texts with decent mentions of some Manassehs on the CDLI. Keep searching and remember that ChatGPT doesn't really understand cases and conjugations in the Akkadian dialects :) (especially for loan words lol).

Oh and "Lugal" is Sumerian. Saying "the Akkadian word Lugal" is simply wrong. This is basic stuff. In Neo-Assyrian cuneiform (I hesitate to say all cuneiform writing systems but it probably is all (that includes non semitic languages)), LUGAL is a logogram for the "king". In this text, since it is written in the Neo-Assryian dialect of Akkadian, that would be šarru in whatever case (nominative, genitive, accusative) is appropriate.

Oh and finally, it is very clear that it is a King Manasseh _of Judah_. Not Assur. Manasseh is not an Assyrian name. If you actually look at the text and just read the goddamn Akkadian, this will be obvious. It clearly says "m^me-na-si-i LUGAL URU.ia-ú-di" not "m^me-na-si-i LUGAL aš-šur^ki". It's not hard to see how wrong the translation is if you just, you know, actually translate the Akkadian. Looking more closely, ChatGPT seems to be unable to associate the given names of kings with place names. Can it not apply its "understanding" of the genitive? Is it just stupid? In fact, many of the place names in the ChatGPT translation are not mentioned anywhere in the column, let alone in this specific section.

From these initial observations, GPT4/ChatGPT seems incapable of understanding rote definitions of Akkadian vocabulary, Akkadian grammatical constructs, determinatives, logograms, et al. The reading of col. V line 55 is incredibly simple. If the now GPT4 powered ChatGPT cannot translate _that_, I suspect it will be a long while before LLMs can even begin producing marginally correct translations of texts written in cuneiform. I think that doing this correctly will require an absolutely massive, tailor-made model. Since the age of giant models is now over [2] (lol) the funding just probably won't be there.

From fighting with this now essay length comment, it is my newly formed opinion that proofreading hallucinated translations is more difficult that just doing the translation yourself. Any work with untranslated cuneiform requires accuracy and a thorough comprehension of the text itself. Errors, even if small can completely ruin whatever point/thesis you were trying to make.

You have to remember that when dealing with cuneiform texts you aren't dealing with one language. You are dealing with whatever the cuneiform was written in, probably some sumerian phrases, maybe the language of the scribe, the languages of your reference works and dictionaries (English, French, German, etc), the idiosyncrasies of the scribe from 4000++ years ago, the idiosyncrasies of the transliterator, missing chunks of tablet, and a writing system that has no modern equivalent. And even just knowing all those things isn't enough, you personally have to be able to fill in all the gaps left by the human actions along the chain of translation. LLMs seem to struggle with the unsaid, barely hinted human influence that is a core part of translating texts written in cuneiform. Will an LLM ever be able to imagine itself as a scribe 3000 years ago, pushing a reed stylus into damp clay to make the signs of an already dead language? Will it understand why that is necessary for translation? Can it comprehend the nuance stacked on nuance that lead to it ingesting whatever text it is going to fail to translate? If it does not, then it is a poor translator. And when working with languages written in cuneiform, a poor translation is worse than useless.

[0] https://www.eisenbrauns.org/books/titles/978-1-57506-209-9.h... [1] AfO Bh. 9 [2] https://www.wired.com/story/openai-ceo-sam-altman-the-age-of...