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
AI Engineer · Event date June 29, 2026 - July 2, 2026

AI Engineer World's Fair - JUNE 29 - JULY 2, 2026 • SAN FRANCISCO, CA

event past event AI EngineeringModel EvaluationAgent Security
Why it matters
June 29, 2026 - July 2, 2026
Event archive

AI Engineer runs the most viewed technical conferences in AI for engineers, with over 10M+ views of our talks online. We are back in SF for the 4th year in a row! This is the one place you can meet with every major frontier lab, leading AI clouds, and AI native/transformed companies — from disruptive AI startups to Fortune 500 AI leaders, and every notable building block in the LLM OS ecosystem.

My takeaway: AI Engineer World's Fair - JUNE 29 - JULY 2, 2026 • SAN FRANCISCO, CA is an event signal. The practical read is to track where researchers, vendors, and operators are putting attention before those themes become standard enterprise guidance.
Keep exploring

More curated notes connected through AI Engineering 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.