Related:
This is in a PR where Shougo, another long-time contributor, communicates entirely in walls of unparseable AI slop text: https://github.com/vim/vim/pull/19413
Thank you for the detailed feedback! I’ve addressed all the issues:
Thank you for the feedback! I agree that following the Vim 8+ naming convention makes sense.
Thank you for the feedback on naming!
Thanks for the suggestion! After thinking about this more, I believe repeat_set() / repeat_get() is the right choice:
Thank you for the feedback. A brief clarification.
Good evening! Thanks for your reply! It’s nice to hear from you!
However in between their conversation, it’s obvious to me that both Shougo and chrisbra were using LLM for their wall-of-text reply.
LLMs are actually quite useful for translation as well as for paraphrasing text for people whose command of the language is not where they want it to be. It’s one of the only uses of LLMs I endorse, because it’s functioning as an assistive technology that enables people to communicate when they otherwise couldn’t. I view it in the same regard as assistive technologies for people with disabilities.
At present day, one may just type in their first language where the result precisely reflects what they really meant. It’s up to the receiving end to interpret it, either learning the language themselves, hire a translator, or use any computer tool - ML to any degree - to assist in understanding.
In my opinion jumping straight to the conclusion that LLM is useful while putting all other aspects (efficiency, accuracy, morality etc.) in disregard is… something worth reconsidering.