Research Blog

Cross-Cutting Themes

All LLM Cognition Safe Computing Formal Optimisation Edge Intelligence Cross-Cutting
Cross-Cutting

Ephemeral Credentials and Zero-Trust AI: Rethinking API Security

Why AI agents need scoped, time-limited credentials — and how perishable implements zero-trust patterns for LLM API access.

securityzero-trustcredentials
Cross-Cutting

Open Science in AI: Why We Publish Everything

The case for radical openness in AI research — reproducibility, falsifiability, and community trust through 24 open-source projects.

open-scienceopen-sourcereproducibility