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 19, 2025

GPT-5.1-Codex-Max evaluation: make safety-case assumptions and scope explicit

analysis Model EvaluationAgent Security
Why it matters

METR’s November 2025 assessment treats GPT-5.1-Codex-Max as an incremental improvement for its specific AI R&D automation and rogue-replication threat models. It combines software-task time horizons, qualitative checks and reasoning-transcript review with developer assurances about training and model affordances. Its forward-looking judgment is conditional on no major trend break. Limited sampling, scaffold differences and imperfect ability to rule out deliberate underperformance prevent treating this historical assessment as a general or current safety certification.

My takeaway: List which safety-case premises are directly measured and which depend on developer assertions. Recheck them after changes to training, tools or scaffolding, and define what evidence invalidates any projection beyond the evaluated model.
Keep exploring

More curated notes connected through Model Evaluation and Agent Security.

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.