Study: People Prefer AI-Written Stories Blindly, Rate Highest When Falsely Told They're Human
EricTopol · x · 2026-08-05
A new study published in Judgment and Decision Making tested whether humans can distinguish between human and AI-authored stories.
- Blind Preference: In a blinded setup with thousands of participants, readers actually preferred AI-generated stories for quality and absorption.
- Labeling Effect: The highest ratings were given when participants were told a story was written by a human, even if it was actually generated by AI.
The research suggests a potential bias against AI creation and an inability to reliably identify it in blind tests.
Related event: Readers Prefer AI-Generated Stories and Fail to Identify Them(4 posts)→
More from AGI Musings
- Lawyer's take: the AI boom will create more legal work, not less — jkubicki · 2026-09-21
- Models will stall near human-level since pretraining data holds nothing smarter, researcher argues — burny_tech · 2026-09-21
- FutureHouse publishes 'Millennium Problems for Biology' as wetlab-verifiable evals for AI — burny_tech · 2026-09-21
- Heidy Khlaaf clashes over 'rogue agent' narrative: bad cybersecurity and reward hacking can coexist — burny_tech · 2026-09-21
- Figma designer pushes back on Eric Schmidt's claim that UI will largely disappear — _AustinCalvert_ · 2026-09-21
- Vercel CEO: 'Fewer lawyers' is the dumbest AI prediction — jkubicki · 2026-09-21