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
NeurIPS · Event date December 11, 2026

NeurIPS 2026: Managing Agents That Manage Agents

event upcoming Agent SecurityModel EvaluationAI Engineering
Why it matters
December 11, 2026
Scheduled event

This NeurIPS workshop meets December 11 in Sydney. It studies systems in which agents design, supervise, or improve other agents, including benchmarks, optimization, and oversight. Security-relevant questions include propagation of misaligned goals, verifiable stopping controls, and the ability of people to supervise increasingly layered agent systems.

My takeaway: Evaluate how authority and failure propagate between supervising and subordinate agents. Look for measurable oversight, enforceable stop conditions, and benchmarks that expose coordination failures instead of reporting only aggregate task success.
Keep exploring

More curated notes connected through Agent Security and Model Evaluation.

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.