I work across frontier AI governance, technical evaluation, public-sector AI, and democratic resilience—with a focus on human agency, manipulation, socially grounded evaluation, and public-interest AI education.
Website · Hugging Face · GitHub projects
FronteraEval
A source-linked, evolving catalogue of frontier AI evaluations for researchers, policy analysts, assurance teams, and evaluators. It keeps evaluation origin, papers, implementations, protocols, evidence reach, and downstream claims distinct.
Browse evaluations · Repository
Spain Reference Personas Frontier
A synthetic reference population and benchmark substrate for evaluating and designing socially grounded AI systems for Spain.
Dataset · Archival DOI · Hugging Face DOI
Cite Spain Reference Personas Frontier
@dataset{guerrero_manchon_2026_spain_reference_personas_frontier,
author = {Guerrero Manchón, Miguel},
title = {Spain Reference Personas Frontier: Synthetic Population and Benchmark Substrate for AI Systems in Spain},
year = {2026},
publisher = {Hugging Face and Zenodo},
version = {0.1},
doi = {10.5281/zenodo.20113558},
url = {https://huggingface.co/datasets/apol/spain-reference-personas-frontier}
}