The Trojan Horse of Free Frontier AIWhen free AI becomes scientific infrastructure, its capabilities can shape which questions get asked—and which alternatives remain worth exploring.
AI Transparency Is a System PropertyA model explanation is not enough. AI transparency must be designed into the surrounding knowledge and decision system so outputs can be traced, challenged and corrected.
Falsification, Not Determinism, Is the Central AI ProblemDeterminism supports reproducibility, but reproducibility is not truth. Knowledge-centric AI requires claims that can be tested, falsified and corrected.
