2026-10-14 01:55 UTC
asking people to edit LLM-generated content gets demonstrably worse results, than asking for authorship from scratch
you'll see lower idea diversity, and lower recall
existing text biases what people are thinking about and reduces the amount and range of things they'll contribute
it's like trying to do decent writing about a challenging topic, while there are people talking in the background
Replies (1)
-
@str0mberg@infosec.exchange 2026-10-14 01:55
to reiterate: the "generate and ask for edits" workflow bakes in /worse/ results than just e.g. giving a couple of handwritten notes for scope and letting people go at it many such cases and studies, don't take my word for it, do your own research etc. but starting with llm-generated text consistently caps the quality of results across a range of tasks and contexts.