Thread context
2 posts in path
Parent
@hongminhee@hollo.social
Open
@hongminhee@hollo.social
I'm writing this in English. Not because English is my first language—it isn't. I'm writing this in English because if I wrote it in Korean, the people I'm addressing would run it through an outdated
30 trillion cells in a trench coat - header picture: the words DONT THINK (a Chemical Brothers album cover) profile picture: person in motorcycle gear riding a cheetah
chaos.social
30 trillion cells in a trench coat - header picture: the words DONT THINK (a Chemical Brothers album cover) profile picture: person in motorcycle gear riding a cheetah
chaos.social
@dngrs@chaos.social
·
4d ago
@hongminhee is there evidence that LLMs are superior to special purpose machine translation models? In my subjective experience the quality of google translate has gone down recently (but I don't know what tech they are using behind the scenes - I think it's likely they shifted to LLM translation but cannot prove it); apart from that I suspect that since LLM training data is largely untagged for translation this would degrade quality vs. purpose built models.
View full thread on chaos.social