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 · January 17, 2025

METR argues that safety evaluation must start before public deployment

analysis AI ComplianceAI Red TeamingAgent Security
Why it matters

METR’s January 2025 analysis identifies risk pathways that a release-time evaluation can miss: stolen model weights, employee misuse and autonomous behavior during internal development or use. It proposes applying assessment, information security and independent oversight throughout the model lifecycle, rather than waiting for public availability. These are threat-model arguments and governance recommendations, not evidence that the hypothetical severe incidents occurred. The practical distinction is between limiting public access and controlling all the environments in which a capable model already operates.

My takeaway: Map internal users, training environments and weight-access paths into the safety review. Establish monitoring and escalation before internal deployment, and identify evidence an independent reviewer needs to assess those controls.
Keep exploring

More curated notes connected through AI Compliance 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.