Topic Hubs
Curated landing pages that gather richards.ai's work on a single research subject — papers, explainers, checklists, glossary entries, and briefs assembled into one navigable cluster with editorial framing.
Agentic AI Security: Prompt Injection, Tool Hijacking, and Voice Agents
This topic gathers richards.ai work on what changes when LLMs gain tools, memory, and peer agents. It collects the threat models, defenses, glossary terms, checklists, executive briefs, and source papers behind multi-agent prompt injection, tool hijacking, memory poisoning, cross-agent infection, and voice-agent jailbreaking. The page offers reading paths for practitioners, engineering leads, researchers, and newcomers, anchored to the current canonical defense reference.
AI Tutoring and Adaptive Learning: Generative Tutors, Scaffolds, and Evaluation
This topic gathers richards.ai's research on generative AI tutors and personalized adaptive learning systems — the lineage from intelligent tutoring systems, the emerging RCT evidence base, and the pedagogical-safety design patterns that distinguish a tutor from a solver. The page offers reading paths for learning-systems engineers, instructional designers, and learning leaders weighing where AI tutoring belongs in real deployments.
AI Binary Analysis: Agentic Reverse Engineering, Decompilation, and Malware Triage
AI binary analysis covers the use of LLMs and LLM agents to recover the behavior, structure, and intent of compiled software. This topic gathers the richards.ai cluster on the subject — the survey paper, explainers on assistive and agentic modes, glossary entries for the core vocabulary, an operational hardening checklist, an executive brief, and a working tool. The page offers reading paths for researchers, practitioners, and security leaders.