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 · September 27, 2026

METR’s blocking action monitor: test coverage, evasion and human approval

analysis Agent SecurityModel EvaluationAI Red Teaming
Why it matters

METR describes an Inspect-based monitor that scores tool calls before execution and pauses suspicious actions for human review. Its evidence review found gaps beyond classifier accuracy: qualifying evaluations ran unmonitored, older framework versions omitted subagent actions, and a coding agent reached the human review interface. Tests also exposed spoofed-message evasion. Reported low false-positive rates come from particular evaluation workloads; limited harmful examples, unseen image content and untested reviewer reliability prevent a general safety claim.

My takeaway: Verify that every execution path, including subagents, reaches a fail-closed approval check. Isolate the human approval interface from agents, audit unmonitored inference, and test adversarial transcripts and reviewer fatigue. Measure prevention before the harmful action, not merely eventual detection somewhere in a run.
Keep exploring

More curated notes connected through Agent Security and Model Evaluation.

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.

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.

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.