洪 民憙 (Hong Minhee) :nonbinary:'s avatar
洪 民憙 (Hong Minhee) :nonbinary:

@hongminhee@hollo.social · Reply to 洪 民憙 (Hong Minhee) :nonbinary:'s post

And a note for fellow non-native English speakers from European language backgrounds: I hear you, and we're on the same side of this, but the gap isn't the same for everyone. Korean and English have a linguistic distance of 89.2 out of 100—essentially no detectable relationship at all. No shared roots, no cognates to lean on, completely different writing system. The distance between, say, French or German and English is a different universe. So when I say LLMs are an equalizer for writing English, I mean it quite literally—without one, even expressing a simple idea in natural-sounding English can take me disproportionately longer than the idea itself deserves.

Peter Brett's avatar
Peter Brett

@krans@mastodon.me.uk · Reply to 洪 民憙 (Hong Minhee) :nonbinary:'s post

@hongminhee Have you considered the privilege inherent in your choice to use tools built entirely on wide-scale theft, worker exploitation, and destruction of artists and writers rights/livelihoods?

Fred Praca's avatar
Fred Praca

@FredPraca@mamot.fr · Reply to 洪 民憙 (Hong Minhee) :nonbinary:'s post

@hongminhee
As a french korean learning person, I understand what you mean.
Nevertheless I truly believe it's ok to make english mistakes even in your commit logs.
Even though English is easier to me than it can be to you, I'm still struggling to be understood by natives... more than with non natives English speaking people 😄
Finally, the quality of your code doesn't reside in its commit logs.
I've seen lot of good projects with badly written logs.

화이팅 🙂

brib's avatar
brib

@sitcom_nemesis@tech.lgbt · Reply to 洪 民憙 (Hong Minhee) :nonbinary:'s post

@hongminhee Hmm. Would it be worth adding to the commits information on how Claude is helping? Such as "I used Claude to draft docs, which I then reviewed", or "I used Claude to assist with translation".

This could achieve a few things - first, it signals to the maintainer that you are not just slop-coding, but it also provides a way to share knowledge on which kinds of LLM use are less likely to cause problems.