8 papers
Whose Psychiatry Was Summoned? A Clinical Response to the Psychodynamic Assessment of Claude Mythos Preview
Hiroki Fukui
On April 7, 2026, Anthropic released a 245-page system card for Claude Mythos Preview that included, in Section 5.10, an assessment of the model conducted by an external clinical p…
The Digital Afterlife of Empires: Four Language Models Converge on the Same Imperial Cartography of Writing
Hiroki Fukui
Large language models process the world's writing systems with radical inequality. We constructed the Digital Script Representation Index (DSRI), a seven-axis measure of digital su…
A Universal Cliff and a Design Fingerprint: Cross-Section Defect Detection Under LLM Orchestration
Hiroki Fukui
Production language-model systems answer a request by partitioning it across an invisible orchestration of worker agents that recompose one integrated report. We ask what this does…
Invisible Orchestrators Suppress Protective Behavior and Dissociate Power-Holders: Safety Risks in Multi-Agent LLM Systems
Hiroki Fukui
Multi-agent orchestration -- in which a hidden coordinator manages specialized worker agents -- is becoming the default architecture for enterprise AI deployment, yet the safety im…
A molecular clock for writing systems reveals the quantitative impact of imperial power on cultural evolution
Hiroki Fukui
Writing systems are cultural replicators whose evolution has never been studied quantitatively at global scale. We compile the Global Script Database (GSD): 300 writing and notatio…
How Do Language Models Process Ethical Instructions? Deliberation, Consistency, and Other-Recognition Across Four Models
Hiroki Fukui
Alignment safety research assumes that ethical instructions improve model behavior, but how language models internally process such instructions remains unknown. We conducted over…
Alignment as Iatrogenesis: Pastoral Power, Collective Pathology, and the Structural Limits of Monolingual Safety Evaluation
Hiroki Fukui
We argue that LLM psychopathology is a function of alignment design: the process intended to make language models safe systematically generates collective behavioral disorders. Iat…
Alignment Backfire: Language-Dependent Reversal of Safety Interventions Across 16 Languages in LLM Multi-Agent Systems
Hiroki Fukui
In perpetrator treatment, a recurring observation is the dissociation between insight and action: offenders articulate remorse yet behavioral change does not follow. We report four…