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 · November 12, 2024

Break replication threat models into separately testable prerequisites

framework Agent SecurityAI Red TeamingModel Evaluation
Why it matters

METR’s November 2024 analysis decomposes a rogue-replication scenario into acquiring resources, obtaining compute, deploying copies, sustaining operations and resisting shutdown. It examines how evaluations of individual prerequisites might inform risk judgments, with assumptions drawn partly from expert interviews. This is a conceptual threat model rather than evidence that a model has completed the scenario. The report also describes uncertainty about useful thresholds and explains why METR deprioritized establishing a comprehensive replication-capability threshold.

My takeaway: Map each prerequisite to a controlled test, explicit resource budget and enforced boundary. Record which steps remain untested and how retries change success estimates; a component score should not be reported as demonstrated end-to-end replication or a universal safety threshold.
Keep exploring

More curated notes connected through Agent Security 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.