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.
Inquiring lines that use this note as a source 3
This note is a source for these synthesized inquiries. Follow a line forward into its question, or open it to trace back to all of its sources.
Related concepts in this collection 2
This note in its neighbourhood — explore the map, then jump to a related concept in the list below.
Click a node to walk · click center to open · click Open in graph to see this note in the full knowledge graph
-
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
Related papers in this collection 8
Papers most semantically related to this note, ranked by cosine similarity in the embedding space.
- “It Felt Like Having a Second Mind”: Investigating Human-AI Co-creativity in Prewriting with Large Language Models
- Has the Creativity of Large-Language Models peaked? —an analysis of inter- and intra-LLM variability —
- Pron vs Prompt: Can Large Language Models already Challenge a World-Class Fiction Author at Creative Text Writing?
- GhostWriter: Augmenting Collaborative Human-AI Writing Experiences Through Personalization and Agency
- Evidence-centered Assessment for Writing with Generative AI
- Thinking LLMs: General Instruction Following with Thought Generation
- Workplace Everyday-Creativity through a Highly-Conversational UI to Large Language Models
- The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas
Original note title
human-AI co-writing follows three creativity stages — ideation illumination and implementation — with iterative return to ideation during writer's block