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 · May 8, 2026

Review of the "Risks from automated R&D" section in the Anthropic Risk Report (February 2026)

analysis Model EvaluationAgent SecurityAI Red Teaming
Why it matters

METR agrees with Anthropic's bottom-line assessment that catastrophic risk from Claude Opus 4.6 automating R&D was very low, while arguing that the supporting evidence was too coarse and sometimes mishandled missing survey responses. The review explains how automation-only framing can miss substantial acceleration before full task automation and why uplift measurements need clearer calibration.

My takeaway: For consequential capability claims, publish granular measurements, sample and missing-data treatment, uncertainty, and calibrated thresholds. Track partial task substitution and workflow acceleration as leading indicators instead of waiting for end-to-end automation, and invite an external reviewer to challenge the argument as well as the benchmark score.
Keep exploring

More curated notes connected through Model Evaluation and Agent Security.

OpenAI News · framework

OpenAI’s Frontier Governance Framework

OpenAI's 22-page Frontier Governance Framework maps its frontier-model processes to California's Transparency in Frontier AI Act and the EU AI Act's general-purpose AI code. It documents lifecycle risk assessment, cyber-offense and other risk tiers, mitigation and residual-risk decisions, critical-incident handling, security risk management, model reporting, external review, responsibility allocation, and change control.

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.

OECD.AI Wonk · guide

A five-step roadmap to closing the AI evaluation gap

The roadmap addresses evaluation results that overstate real-world performance or fail to transfer across deployment contexts. Its five steps balance standardized and local tests, evaluate throughout the lifecycle, build qualified assurance and communication capacity, tailor tests to each value-chain actor and technology, and use a coordinated, trusted process for updating methods.