Dead Comment
Another ergonomic benefit is scripting. For example, if I'm running a series of scripts to generate figures/plots, LaTeX will pick up on the new files (if the filename is unmodified) and update those figures after recompiling. This is preferable to scrolling through a large document in MS Word and attempting to update each figure individually.
As the size and figure count of your document increases, the ergonomics in MS Word degrade. The initial setup effort in LaTeX becomes minimal as this cost is "amortized" over the document.
I'm still sour about the 3 days it took me to have something usable for my thesis, and I was starting from an existing template. And it's still not exactly how I want it to be; I gave up on addressing a bug in the reference list.
Dead Comment
Not sure that's even true. Mistral is known to be a really hard-working place
Dead Comment
Since what's proper and meaningful depends on a lot of variables. Testing these, keeping track of them, logging and versioning take it from "vibe prompting" to "prompt engineering" IMO.
There are plenty of papers detailing this work. Some things work better than others (do this and this works better than don't do this - pink elephants thing). Structuring is important. Style is important. Order of information is important. Re-stating the problem is important.
Then there's quirks with family models. If you're running an API-served model you need internal checks to make sure the new version still behaves well on your prompts. These checks and tests are "prompt engineering".
I feel a lot of people take the knee-jerk reaction to the hype and miss critical aspects because they want to dunk on the hype.
On the other hand, prompt tweaking can be learned in a few days just by experimenting.