4 papers
Measuring in-context algorithmic reasoning in language models against an exact Bayes-optimal reference
Hector Zenil, Luan Ozelim
Whether large language models perform algorithmic inference or pattern completion is hard to test, because most benchmarks supply answers but no distributional reference for what t…
Can Complexity and Uncomputability Explain Intelligence? SuperARC: A Test for Artificial Super Intelligence Based on Recursive Compression
Alberto Hernández-Espinosa, Luan Ozelim, Felipe S. Abrahão +1
We introduce an increasing-complexity, open-ended, and human-agnostic metric to evaluate foundational and frontier AI models in the context of Artificial General Intelligence (AGI)…
Assembly Theory Reduced to Shannon Entropy and Rendered Redundant by Naive Statistical Algorithms
Luan Ozelim, Abicumaran Uthamacumaran, Felipe S. Abrahão +4
Assembly Theory (AT) and its central measure, the assembly index (Ai), represent an invaluable opportunity to address some of the most persistent and widespread conflations and mis…
Non-Random Data Encodes its Geometric and Topological Dimensions
Hector Zenil, Felipe S. Abrahão, Luan C. S. M. Ozelim
Based on the principles of information theory, measure theory, and theoretical computer science, we introduce a signal deconvolution method with a wide range of applications to cod…