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
Berkeley RDI · Event date August 1, 2026 - August 2, 2026

Berkeley Agentic AI Summit 2026

event past event Agent SecurityAI EngineeringModel Evaluation
Why it matters
August 1, 2026 - August 2, 2026
Event archive

Berkeley RDI's two-day Agentic AI Summit covers the full agent stack, from foundation models, infrastructure, and frameworks to evaluation, real-world deployment, safety, and security. The UC Berkeley program combines research and industry sessions and offers a public livestream.

My takeaway: Prioritize sessions that expose operational evidence: how agents receive identity and authority, how tool and memory boundaries are enforced, which end-to-end evaluations predict production behavior, and how failures are contained and replayed. Separate demonstrated controls from platform roadmaps and adoption claims.
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.

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.

OpenAI News · framework

OpenAI’s Frontier Governance Framework

OpenAI's 22-page Frontier Governance Framework maps its frontier-model processes to California's Transparency in Frontier AI Act and the EU AI Act's general-purpose AI code. It documents lifecycle risk assessment, cyber-offense and other risk tiers, mitigation and residual-risk decisions, critical-incident handling, security risk management, model reporting, external review, responsibility allocation, and change control.