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
AGI Summit · Event date July 18, 2026 - July 19, 2026

AGI Summit SF 2026

event past event Agent SecurityModel EvaluationAI Red Teaming
Why it matters
July 18, 2026 - July 19, 2026
Event archive

Archive entry for AGI Summit SF 2026, held July 18–19 at San Francisco’s Palace of Fine Arts. The two-day program covered AI agents, foundation models, infrastructure, robotics, open source, safety, and alignment, with sessions spanning agentic misalignment, coding agents, continual learning, model evaluation, enterprise security, and AI sovereignty.

My takeaway: Use the summit archive as a discovery index, not as evidence for session claims: follow the official agenda to primary slides or recordings as they are released, then evaluate technical assertions against papers, system cards, benchmarks, and reproducible demonstrations. No official recording archive was available when this entry was added on July 21.
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.

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.