You are currently viewing An Example of How Helpful LLMs are Becoming

An Example of How Helpful LLMs are Becoming

I’m in the process of translating a fourteenth-century text, Wang Dayuan’s 1349 Brief Treatise on the Island Barbarians (Daoyi zhilue 島夷誌略), and I do this by putting passages in Grok, and then checking its translations.

Today I was working on a section on “Jiaozhi,” the area of the Red River delta, when Grok gave me the following translation:

“Among the common people, sixty-seven cash are reckoned as equivalent to one tael of Zhongtong silver. The official rate is fixed at seventy” (民間以六十七錢折中統銀壹兩。官用止七十為率。)

I don’t know what “Zhongtong silver” (Zhongtong yin 中統銀) is, so I wasn’t sure if this was correct. In general, I know very little about the history of money and currencies, so this is something I always need to check.

The first thing I always do is to check a good online Chinese-Chinese dictionary (zdic).

 

What came up was not “Zhongtong silver” but “Zhongtong bills/notes” (Zhongtong chao 中統鈔), with the definition saying “Paper money issued during the Zhongtong 中統 reign period of the Yuan dynasty, in two types: jiaochao 交鈔 and yuanbao chao 元寶鈔.”

Ok, so from that I realized that “Zhongtong” meant a Yuan dynasty era, and looking that up, I find that it was from 1260 to 1264, about a century before the text I’m looking at was compiled.

However, I wasn’t sure why the text I’m looking at had Zhongtong “silver” when there was a kind of currency that was created in the Zhongtong era that was called “bills/notes.”

So, I asked ChatGpt, “What was 中統銀?”, meaning “What was Zhongtong silver?” It thought for 25 seconds, and then for some reason it responded in Chinese as follows:

1) As a conversion/pricing unit equivalent to “taels of silver” (銀兩)

In Yuan-dynasty materials—and in Yuan authors’ descriptions of foreign polities—transaction values are often expressed by converting them into “so many taels of silver.” In this sense, “one tael of Zhōngtǒng silver” (中統銀一兩) usually means “the value of one tael of silver as reckoned under the Yuan’s Zhōngtǒng system (or with Zhōngtǒng paper money as the benchmark).

A typical example is Wang Dayuan’s Dǎoyí zhìlüè (島夷誌略), in its entry on Jiaozhi (Giao Chỉ / Đại Việt), which says:

“Copper cash circulates for use. Among the people, sixty-seven cash are converted as one tael of Zhōngtǒng silver; for official use, they stop at taking seventy as the standard rate.”

That is: locally, copper cash is the circulating medium, but there is an exchange-rate conversion between copper cash and “one tael (Zhōngtǒng) silver” (private rate 67 cash = 1 tael; government rate 70 cash = 1 tael).

2) Possibly a corrupted/mistaken writing for “Zhōngtǒng paper money” (中統鈔)

Some scholars—especially those working with surviving paper-money artifacts and textual/edition collation—point out that what is commonly attested in the Yuan is Zhōngtǒng chāo (中統鈔; Zhōngtǒng Yuánbǎo Jiāochāo 中統元寶交鈔). In some documentary contexts, “Zhōngtǒng silver” (中統銀) may therefore be the result of a scribal or printing error in which 鈔 was miscopied/misprinted as 銀. Hence one must judge from context.

3) (Supplement) “Zhōngtǒng silver-currency goods” (中統銀貨): a proposed silk-based “currency” equivalent to silver

Japanese-language scholarship also mentions a view that, early in Qubilai’s reign when the Zhōngtǒng paper-money system was being implemented, there was a proposal or accompanying concept of “Zhōngtǒng silver-currency goods” (中統銀貨)—made of silk and treated as equivalent in value to silver.
(This claim usually appears in discussions of the design of early Yuan paper-money policy and the intended “reserve/redemption” mechanisms behind it.)

HOLY S%^&!!!!!

Not only does that answer every question that I had in my mind and more. . . it’s all backed up with links to reliable sources of information.

This didn’t happen a year ago. I’m not sure when this started, but it hasn’t been that long.

So, now when I’m working, what I’ll do is to have different LLMs open, and I’ll throw a question into one and let it think about it, and then I’ll ask another to translate a passage, and then I’ll check back to see how the first LLM responded to my question, etc.

Is this different from Googling for information?

To some extent, “no,” because I probably could have figured all this out without an LLM, but it would have taken much longer than 25 seconds, and it would have interrupted my work.

Now, it’s becoming a seamless process. I don’t necessarily follow up on all the links and information that I’m informed about, but that stuff all seeps into the back of my brain, and I know that it’s not only “out there” if I need it, but that I can search for and find it quickly again in the LLM that I’m using.

Subscribe
Notify of
guest

2 Comments
Oldest
Newest Most Voted
Inline Feedbacks
View all comments
Lucas
Lucas
1 month ago

Sounds easy. One could also just read what the official history of the Yuan 元史 offers on 鈔法, or the exchange rates described in Yuan wenlei 元文類. Just trying to preserve some self-worth here faced with machine competition…
Yes, it took more than 25 seconds to find these references, about 35 secs to access the relevant databases, but then Chinese studies requires patience. And there is not much more on that specific currency.
If you have access to the Daoyi zhilüe with commentary (Daoyi zhilüe jiaoshi), you will find that in the description of Penghu (Pescadores?) the currency is referred to as Zhongtong qianchao 中統錢鈔 to which is added an informative discussion by commentator Su Jiqing 蘇繼廎. In the descriptions of Luohu 羅斛 and Wuye 烏爹 a Zhongtong chao 中統鈔 is mentioned, which may or may not be correct for Zhongtong yin. It is obvious, if we want to believe the Daoyi zhilüe (which has a somewhat sketchy transmission history) that some foreign people were still using “dated” currency in the middle of the 14th century.