Unverified50% confidenceFactExact time
AI puzzles are a new evaluation format between a benchmark and an open-problem list, proposed by researcher Jarek Duda, built with the aperiodic order research field as a pilot to construct a tiered, ladder-style puzzle set.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/25/2026
First Seen
Valid until: 1/23/2027
Sources
Related Entities
Related Claims
UnverifiedThe open levels of AI puzzles provide the complete materials needed to solve the problem: strong numerical evidence, known failed paths, relevant files, and a machine-checkable success criterion.76% similarUnverifiedThe ladder design of AI puzzles arranges questions in the same research field by difficulty from human level (solvable with pen and paper) to ASI level (fully open), with each level genuinely harder than the previous one.73% similarUnverifiedMathematical problems currently solvable by AI typically share the characteristics of having solutions of finite length, being obtainable through combinatorial search or constructive methods, or being natural extensions of existing technical frameworks.71% similarVerifiedModern AI mathematical systems adopt a generate-and-verify closed-loop architecture, leveraging the asymmetry of mathematical problems being 'hard to generate but easy to verify'69% similarUnverifiedWhen faced with headlines claiming AI has solved a world-class problem, asking which specific version of the problem was addressed is an effective method for evaluating AI research results.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1097056API
curl https://kongchang.com/api/v1/knowledge/claims/1097056MCP
get_claim(id=1097056)