Depends on what your prose is for. If it's for documentation, then prose which matches the expected tone and form of other similar docs would be clichéd in this perspective. I think this is a really good use of LLMs - making docs consistent across a large library / codebase.

▲

minimaxir 8 hours ago | parent | next [-]

I have been testing agentic coding with Claude 4.5 Opus and the problem is that it's too good at documentation and test cases. It's thorough in a way that it goes out of scope, so I have to edit it down to increase the signal-to-noise.

▲

girvo 7 hours ago | parent | next [-]

The “change capture”/straight jacket style tests LLMs like to output drive me nuts. But humans write those all the time too so I shouldn’t be that surprised either!

	▲	mulmboy 2 hours ago \| parent [-]
		What do these look like?

▲

diamond559 4 hours ago | parent | prev [-]

If the goal is to document the code and it gets sidetracked and focuses on only certain parts it failed the test. It just further proves llm's are incapable of grasping meaning and context.

▲

danenania 8 hours ago | parent | prev | next [-]

A problem I’ve found with LLMs for docs is that they are like ten times too wordy. They want to document every path and edge case rather focusing on what really matters.

It can be addressed with prompting, but you have to fight this constantly.

	▲	bigiain 7 hours ago \| parent [-]
		I think probably my most common prompt is "Make it shorter. No more than ($x) (words\|sentences\|paragraphs)."

▲

dcre 8 hours ago | parent | prev [-]

Docs also often don’t have anyone’s name on them, in which case they’re already attributed to an unknown composite author.