I would agree with this statement before LLMs. Reading manuals can take time, be messy, and are sometimes hard to understand.

Now, I can simply ask any LLM to write the command, and understand any following issues or questions.

For example, my OS records videos as WEBM. Using the default settings for transforming to MP4 usually fails from a resolution ratio issue. I would be deadlocked using this library.

It really isn't that hard anymore.

I sometimes use LLMs to generate commands, and it generally works. But a common issue is that it throws in extra options because they are very commonly used - even if they're not necessary or relevant to my actual situation. So if you don't go through and check them all, you get this kind of unchecked cruft in your scripts that may later cause a problem.

Except what if you don’t really grok those ffmpeg flags and the LLM tells you something wrong - how will you know? Or more common, send you down a re-encode rabbit hole when you just needed a simple clipping off the end?