AI Red Team Engineering notes, research references, and field notes on AI systems, responsible AI, governance, and compliance.
Global search

Search AI Red Team

Search across the complete knowledge base.

Enter at least two characters to begin.
↑↓ select Enter open Browse the full research archive
METR · October 6, 2025

QA monitoring experiments show how evasion depends on tasks and monitor strength

analysis Model EvaluationAI Red TeamingAgent Security
Why it matters

METR’s October 2025 experiments test whether models can complete question-answering tasks while concealing a secondary objective from a monitor. Results vary with task difficulty, reasoning allowance and attacker instructions; models could evade more easily when the side task needed little explicit reasoning. A small model trained against one monitor transferred poorly to a stronger monitor. Detection was calibrated near a low false-positive rate, making the operating point part of the result. These artificial side tasks provide a controlled test of oversight, not a measured rate of covert misconduct in deployed agents.

My takeaway: Evaluate monitors at a stated false-positive rate across easy and difficult tasks. Test adaptive attackers and stronger held-out monitors before interpreting success against one monitor as a general evasion capability.
Keep exploring

More curated notes connected through Model Evaluation and AI Red Teaming.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

OpenAI News · framework

A blueprint for democratic governance of frontier AI

OpenAI proposes a three-part U.S. frontier-AI governance model: harmonize emerging state safety laws into a federal baseline, strengthen CAISI as an evaluation and standards institution, and coordinate a broader resilience program. Proposed controls include severe-risk evaluations, transparency reports, independent audits, safety-incident reporting, model-weight security, whistleblower protection, and periodic technical assessments.