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
NeurIPS · Event date December 6, 2026 - December 13, 2026

NeurIPS 2026

event upcoming Model EvaluationAdversarial MLAI Compliance
Why it matters
December 6, 2026 - December 13, 2026
Scheduled event

NeurIPS 2026 runs in Sydney December 6–12, with Atlanta and Paris satellite programs December 9–13. Sydney’s main conference is December 8–10 and its workshops are December 11–12; satellite workshops fall December 12–13. Several Sydney workshops examine agent security, trustworthy evaluation, and supervision of autonomous systems.

My takeaway: Choose the location and workshop before booking: Sydney and the satellite programs have different schedules. The focused agent-security and evaluation workshops have separate calendar entries with their exact Sydney dates.
Keep exploring

More curated notes connected through Model Evaluation and Adversarial ML.

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.