Study: ChatGPT dating advice beats humans blind, but AI label flips ratings
ipeirotis · x · 2026-09-10
A preregistered study by Osborne & Bailey (Scientific Reports, 2025; 5 experiments, N=1,722) finds that blind raters judge ChatGPT's advice as higher quality, more effective, and more authentic than human advice — even in dating/relationships, where people strongly prefer human advice. Provenance labels flip judgments: the same poems rated worse once labeled AI-generated, even though AI poems actually scored better. People's aversion is provenance bias, not quality.
Related event: ChatGPT Beats Humans in Blind Evaluation of Relationship Advice(2 posts)→
More from Research
- StereoPolicy learns robot 3D perception from stereo pairs, hits 59% success — TheZachMueller · 2026-09-10
- Why counting breaks LLMs: the minimal attention program needs two indices — ctjlewis · 2026-09-10
- Proof verifiers trusted for humans may fail against AI-crafted exploit proofs — yoavgo · 2026-09-10
- Columbia DAP Lab's VLDB 2026 keynote: agentic data environments as the next research frontier — adityagp · 2026-09-10
- Nupur Kumari, author of first thesis on customizing generative image models, joins OpenAI — junyanz89 · 2026-09-10
- Frank Nielsen's info geometry textbook offers a foundational ML entry, now on ChapterPal — burkov · 2026-09-10