BVSR: less context during ideation makes AI scientists more creative, Stanford study
james_y_zou · x · 2026-11-11
Stanford researchers (led by Kevin GuoweiXu and Jiaru Zou, with Pan Zou and James Zou) introduce BVSR — Blind Variation, Selective Retention — a discovery framework inspired by classic human creativity theory. AI scientists are usually given maximal task context, which anchors them on familiar approaches. BVSR instead restricts task information during ideation and injects experimental evidence only at the selection stage, judging ideas on originality, usefulness and non-obviousness. It plugs into existing AI-scientist workflows.
Related event: Stanford's BVSR Framework Boosts AI Scientist Creativity(3 posts)→
More from AGI Musings
- CS enrollment at elite colleges down up to 43% since ChatGPT, dropping faster post Claude Code — zack_overflow · 2026-11-11
- Qantas to cut 850 Australian jobs and outsource to India under AI-driven overhaul — nordicinst · 2026-11-11
- iamtrask: Email is the 'dial-up' version of the AI internet — iamtrask · 2026-11-11
- AI didn't break education — education was measuring the wrong things all along — Yamapama · 2026-11-11
- repligate notes Christiano was labeled an "OpenAI board member" — repligate · 2026-11-11
- Cognitive scientists find AI generates ideas faster, but human teams stay more creative — CurieuxExplorer · 2026-11-11