FID-075 · Open question
How do autonomy, tool access, resource budgets, and human assistance change an AI system's cybersecurity capabilities and the risk it creates?
Research in development
Explore a specific question, the approach we propose, and where your expertise could help. Each brief states its current stage.
Cybersecurity
Protocol developmentFide is developing a study of whether targeted retesting catches meaningful performance declines, or gives false reassurance. We begin with AI malware-report analysis, comparing smaller retests against complete benchmark reruns.
Protocol and evaluation tooling in development. No model-performance findings yet.
Updated
A model score does not identify what a deployed agent can accomplish with tools, time, permissions, and collaborators. Separating these factors could make independent evaluations more informative without treating task success as proof of real-world harm.
Working hypothesis
A proposition to test, not a finding.
System configuration will change measured capability and boundary violations beyond model choice alone. The null is that these changes add no reproducible explanatory power over a model-only baseline.
Proposed method
Needed controls
Relationship to existing work
FID-074 provides the runtime-assurance frame. FID-076 tests controls rather than capability; FID-077 examines the evidence needed after an incident.
Expected outputs
Open questions
Related calls
FID-064
How does AI mediation change a community's ability to integrate dispersed knowledge, preserve epistemic diversity, surface dissent, revise judgment, and make accountable decisions? Under what conditions does it strengthen collective inquiry, and under what conditions does it create correlated error, false consensus, or concentrated authority?
FID-089
Which behavioral, internal, and developmental observations distinguish candidate consciousness mechanisms from learned reporting, role simulation, and generic capability, and how sensitive are those observations to elicitation and training?
FID-090
What distinguishes stable functional preferences or valence-related mechanisms from prompt compliance and performance artifacts, and what additional evidence would be needed before treating them as welfare-relevant?
Open question
Primary need: security research, evaluation engineering, threat modeling, statistical design
New to the Contributor Network? Share a short private introduction once, even if you join several calls. You can join the public discussion while introducing yourself.
Join the Contributor Network ↗