Blind Test: AI-Written Stories Preferred Over Human, Readers Can't Tell the Difference
EricTopol · x · 2026-08-05
In a study, thousands of participants rated stories written by humans or AI in a blinded manner. They preferred AI-generated stories for quality and absorption. Ratings were highest when participants were told the story was written by a human, even though it was actually by AI. Eric Topol commented that participants couldn't tell the difference, performing worse than a coin flip.
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