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
[un]prompted · Event date October 27, 2026 - October 29, 2026

[un]prompted II

event upcoming AI Red TeamingAgent SecurityAI Compliance
Why it matters
October 27, 2026 - October 29, 2026
Scheduled event

[un]prompted II is a practitioner-led AI-security conference in San Francisco organized around building, breaking, operating, governing, and training AI systems. Its review criteria favor production architecture, metrics, failures, demonstrations, code, and prompts over pre-deployment speculation.

My takeaway: This is a strong source for field evidence if the final agenda maintains that bar. Capture concrete attack preconditions, control failures, detection and recovery data, and implementation artifacts from accepted talks; verify the final agenda before travel.
Keep exploring

More curated notes connected through AI Red Teaming 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.