AI-Generated Stories Beat Human Ones for Readability, Study Finds
nordicinst · x · 2026-08-05
A study published in the journal Judgment and Decision Making and reported by The Guardian reveals that AI-generated short stories outperformed human-written ones in ratings of readability and quality.
- Methodology: 1,682 participants were asked to read short stories authored by either humans or ChatGPT, but researchers occasionally provided misleading information about the true author.
- Key Findings: Readers rated AI-generated stories as more absorbing and of higher quality. Researchers attribute this to the AI's simpler writing style, which is easier to digest.
- Psychological Bias: Despite the objective quality of AI text, participants consistently gave higher overall ratings to stories they were told were written by humans.
The researchers concluded that while AI can now generate high-quality short fiction, this does not render human authors obsolete, as human creativity still holds irreplaceable value.
Related event: Readers Prefer AI-Generated Stories and Fail to Identify Them(4 posts)→
More from Research
- Anthropic Sets Up Bay Area Wet Lab, Plans to Have Claude Run Experiment Robots — FinanceYF5 · 2026-09-21
- KLPO: a critic-free, single-rollout RL method for agentic LLMs, framed as 'Q* solved' — inductionheads · 2026-09-21
- FutureHouse publishes 'Millennium Problems for Biology' as wetlab-verifiable evals for AI — burny_tech · 2026-09-21
- No scientific test for consciousness exists even in humans — how can we declare AI unconscious? — burny_tech · 2026-09-21
- Formal Reasoning in AI: Song guest-lectures Virginia Tech course, slides public — wellecks · 2026-09-21
- Biologist: FutureHouse's Bio Millennium List Is Too Narrow — Really Just Synbio — burny_tech · 2026-09-21