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
Google DeepMind Blog · May 19, 2026

Co-Scientist: A multi-agent AI partner to accelerate research

analysis Agent SecurityAI EngineeringModel Evaluation
Why it matters

Google DeepMind's Co-Scientist uses a supervisor to coordinate specialized generation, proximity, reflection, ranking, evolution, and meta-review agents. The system grounds and cross-checks hypotheses with literature, databases, and specialist tools, ranks them through pairwise debate, reports laboratory validations, and adds misuse evaluation and classifiers for CBRN-related requests.

My takeaway: Treat the design as a multi-agent evaluation case study rather than evidence that internal debate guarantees correctness. Preserve source provenance and complete decision traces, independently validate high-impact hypotheses, gate risky tools and CBRN domains, and test for poisoned retrieval, hallucinated citations, correlated-agent errors, circular consensus, ranking manipulation, and unsafe goal decomposition.
Keep exploring

More curated notes connected through Agent Security and AI Engineering.

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.