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 · August 7, 2025

METR’s GPT-5 assessment combines capability tests with a limited safety argument

analysis Model EvaluationAI Red TeamingAI Compliance
Why it matters

METR’s 2025 predeployment assessment examines GPT-5 through autonomous task evaluations and investigations of research capabilities, replication and strategic sabotage. The report combines observed behavior with information supplied by the developer to assess specific threat models. It also explains where short evaluation windows, benchmark saturation, incomplete elicitation and limited testing of evasion weaken the conclusions. The assessment does not cover every misuse domain or establish broad alignment. Its reusable contribution is the structure of an evidence-based safety argument, including explicit dependencies on developer assurances and unresolved uncertainty.

My takeaway: For each safety claim, separate independently observed behavior from developer-provided evidence. Record untested threat models and the conditions that would invalidate the argument after a model or scaffold changes.
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.