How do writers use AI through different creative stages?
This study explores whether writers deploy large language models differently depending on their creative needs—from generating initial ideas to organizing thoughts to drafting final text. Understanding these patterns reveals how humans and AI can complement each other's strengths.
LLMs were most intensively used for Ideation when participants initially had no ideas or only a vague picture. If they had existing thoughts, most preferred using the LLM as an Illumination tool to organize, summarize, and reify those thoughts. Once an idea could be articulated, participants experimented during Implementation. The three stages often occurred linearly but the process was iterative — participants returned to Ideation whenever they hit writer's block during Implementation. Unexpected or "failed" LLM outputs from any stage also served as inspiration, implicitly triggering new Ideation.
This maps onto the vault's ideation-evaluation dissociation: since Can LLMs generate more novel ideas than human experts?, the co-writing finding suggests humans naturally use LLMs for what they're good at (combinatorial ideation) while reserving evaluation for themselves. The "second mind" experience described by participants is the custodial relationship in creative form — the human steers, the AI generates, and the human evaluates.
Source: Co Writing Collaboration Paper: "It Felt Like Having a Second Mind"
Related concepts in this collection
-
Can LLMs generate more novel ideas than human experts?
Research shows LLM-generated ideas score higher for novelty than expert-generated ones, yet LLMs avoid the evaluative reasoning that characterizes expert thinking. What explains this apparent contradiction?
co-writing naturally separates the two
-
Does AI reshape expert work into knowledge management?
As AI generates knowledge at scale, does expert work shift from creating new understanding to curating and validating machine outputs? This matters because curation and creation demand different cognitive skills.
co-writing as creative custodianship
Click a node to walk · click center to open · click Open full network for a force-directed map
Original note title
human-AI co-writing follows three creativity stages — ideation illumination and implementation — with iterative return to ideation during writer's block