People spent considerable amount of effort developing systems that separate contents from styles (latex, html/css, etc). And with Python people think it’s a good idea to encode contents as styles…
What's your suggestion then? For China to reduce its population by 3/4 (wasn't China heavily criticized for enforcing birth-control?), or to acknowledge that Chinese citizens (or those of any other country with a population greater than that of the US) don't deserve to enjoy the same standard of living as US citizens?
> Japanese has a lot of compound words of Chinese origin, where two or more kanji appear as a set.
In the original Chinese language, a "word" mostly consists of a single character. Interestingly, many of the compound words commonly seen in modern Chinese were in fact coined by the Japanese scholars during their attempts to translate western writings around the 19th century and were later "imported" back into Chinese language. Interestingly, the two examples in the article, "art" (美术) and "science" (科学) are both of Japanese origin, though one can still tell whoever coined the terms chose the individual characters due to their meaning being relevant to the concepts the words are describing.
According to this paper https://www.lingref.com/cpp/decemb/5/paper1617.pdf the natural linguistic evolution towards compounds in Chinese was well under way by the time of Middle Chinese (~800CE). And most of the cultural exchange with Japan happened after that.
That’s true, but many Japanese terms for describing the modern world were mass-imported into Chinese during the late Qing and Republican eras (think 1900-1930).
The Chinese republicans looked towards Japan as a model for how to develop, and part of that was importing new lexicon wholesale, since Japanese scolars had already helpfully transliterated Western concepts into new compounds during the Meiji era.
And lets not forget the enormous number of English (and other) words imported into Japanese that look crazy to a non-Japanese speaker, but once you spell out the katakana you realize it is just English (e.g. ホテル / hoteru = hotel, シングルルーム / shingururūmu = single room)
Except that a weather forecasting model can't experiment on weather, but a LLM system may be designed to be able to perform experiments and take feedbacks?
This is somewhat expected to be honest. I am rather pessimistic on the future solutions to such issues though. I can see only one possibility going forward: camera sensor manufactures will either voluntarily or forcibly implement hardware that inject cryptographic "watermarks" to the videos produced by their cameras. Any videos that do no bear valid watermarks are considered potentially "compromised" by GenAI.
