AI alignment: stating what AI must do, and checking it by machine.
- Site: mariobrcic.com
- ORCID: 0000-0002-7564-6805
- Canonical identity: mariobrcic.com/identity/
Associate Professor at FER (University of Zagreb). The work has four parts: stating exactly what AI must do, building the tools that check it (formal verification, interpretability of language models), finding the limits no alignment method can get past, and asking who sets AI's goals.
- AI Safety Formalization Atlas — an open Lean 4 library of machine-checked AI-safety mathematics, with every result's source and scope on record. Documentation.
- VALOR — FER research project on value alignment and interpretability of large language models. First output: llm-political-steerability, the reproducibility package for Auditing Alignment Controllability in LLMs via Political Axes (AIES 2026).
- Modern Algorithm Design — a textbook on designing algorithms from reusable primitives, and on stating precisely what an algorithm must guarantee. Its code, with each structure in Python, Rust and Lean, is in algodesign.
- minimap2 — portable SIMD (sse2neon → SIMDe) + non-SIMD build, enabling ARM/aarch64 support: lh3/minimap2#597
- spoa — portable SIMD via SIMDe (rvaser/spoa#29) and a CPU dispatcher across SIMD architectures (rvaser/spoa#33)
- pybliometrics — generalized abstract retrieval by different Scopus identifier types: pybliometrics-dev/pybliometrics#71
- Explainable optimization (2018) — tracking-predictive-gantt: a visual-explainability method for stochastic scheduling (ECDF uncertainty and counterfactual overlays). The failure modes it exposed led to a follow-up scheduler with gains of up to ~770% over the prior state of the art. DOI
The pinned repositories are the packaged, reproducible work. The others range from active research to teaching material, at varying polish. Questions and collaboration are welcome.




