FAR Paradigm: AI Automatically Filters Worthwhile Math Conjectures
rohanpaul_ai · x · 2026-08-31
As AI's mathematical capabilities improve, the bottleneck has shifted from solving problems to deciding which ones are worth the compute. This paper proposes FAR (Find, Attempt, Recommend), a new human-AI discovery paradigm. Instead of humans pre-selecting a single problem, the system searches, filters, and recommends conjectures based on a research direction. In a combinatorics pilot, the pipeline processed 5,245 papers, extracting and filtering down to 4,717 viable open conjectures and surfacing 598 potential resolutions, aiming to alleviate the scarcity of expert review resources.
Related event: FAR Framework Helps AI Rank Which Math Conjectures Deserve Attention(2 posts)→
More from AGI Musings
- Jeff Clune: Moving the Goalposts Will Be Humanity's Last Job — jeffclune · 2026-10-16
- Nature paper uses language models to map single neurons behind human language — raphaelmilliere · 2026-10-16
- 3SUM record falls to O(n^1.921), Lean-verified — but will it yield usable algorithms? — iskander · 2026-10-16
- Terence Tao predicted AI would be a mathematician's copilot in 3 years — reality outran him — abhishekcode42 · 2026-10-16
- Experts Across Fields Estimate 1-16% AI Catastrophe Risk by 2100, Survey Shows — ben_j_todd · 2026-10-16
- Experts put global AI catastrophe risk before 2100 at 5%, LEAP survey finds — ben_j_todd · 2026-10-16