Research & Blog

Red-Team Field Notes

Attack techniques and failure modes in production AI systems.

All Future Predictions Deep Tech Governance & Policy Red-Team Field Notes

FIELD NOTESMar 15, 2025 · 6 min read

Slopsquatting: How AI Package Attacks Work and How to Stop Them

Slopsquatting turns an AI-invented package name into a software supply-chain attack. Here is the attack path and the dependency gate that stops it before install.

Alex Georges, PhDRead →

FIELD NOTESJan 22, 2025 · 5 min read

When AI Therapy Goes Wrong: Stanford Reveals Chatbots Are Encouraging Delusions and Self-Harm

New research shows AI "therapists" fail catastrophically at crisis intervention, validate psychotic delusions, and stigmatize mental illness. The risks are becoming impossible to ignore.

Alex Georges, PhDRead →

Get new writing by email.

Occasional notes on AI risk, adversarial testing, and governance. No marketing drip.