I thought 'how bad can it be?', yet only three paragraphs in "a specifier now names a repository rather than choosing a transport"
If you're going to serve us slop then at least serve us good slop, give it a pass through GPT 5.6 to clean up the English.
What’s the problem with that? Seems to make sense to me with the example and it’s important to point out. I’d expect an llm to explain in more detail to be honest.
Maybe the author is a non-native English speaker, and this enables him to communicate things he's not able to do himself. Should OSS maintainers start hiring professional translators? Are you going to fund that?
We really should stop jumping to conclusions and shaming people for using these tools just because you don't like the language of the LLM. How is a non native speaker meant to determine what is English slop and what isn't?
I should also note, I am a native speaker. There's absolutely nothing wrong with what's written in the part you chose to paraphrase, and it makes sense to me.
I remember the most interesting things to do with 3.5 Turbo was to ask it to rewrite paragraphs in different styles.
Why can modern LLMs basically not do that anymore? They each have their own very particular writing style?
It it all just beaten out of them in post training?