Humanlike AI in Collaborative Writing

This comparative user study (n=48) examines how the temporal and visual dimensions of AI collaboration shape the experience of writing tasks, revealing that humanlike design features in AI agents create both positive social expectations and unexpected social costs.

The Humanlike-to-Machinelike Spectrum

Three AI-assisted text editor variants were tested along two dimensions:

Temporal: synchronous (humanlike) vs. asynchronous (machinelike) suggestions

Visual: presence (humanlike) vs. absence (machinelike) of a cursor

Synchronous suggestions increased efficiency but led to contextual misalignment — the AI's suggestions didn't fit the writer's intent. A visual cursor improved perceived intent understanding but evoked feelings of surveillance that participants described as "eerie." This maps onto emerging concerns in AI Peer Feedback Systems about the social dynamics of AI interaction in educational contexts.

Implications for AI Writing Tools

These findings have direct relevance for LLM co-writing tools and the broader ecosystem of Generative AI writing assistants. The uncanny valley effect in AI collaboration suggests that anthropomorphic design choices must be paired with careful expectation management — without the mutual alignment natural in human-human collaboration, humanlike features can backfire.

The study also connects to research on AI social fluency: users' inability to detect AI teammates above chance takes on new significance when AI interfaces are designed to feel more human. If students can't reliably distinguish human from AI collaborators, the design choices described here could amplify both the benefits and costs of AI in Writing Education.

Connected Concepts

Writing Education

Generative AI

Connected Articles

AI Peer Feedback Systems

Mindcopilot LLM Co Writing

Socially Fluent AI Identity Detection

Citation