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
METR · September 26, 2023

Responsible scaling policies: connect evaluation triggers to accountable action

framework AI ComplianceModel Evaluation
Why it matters

METR’s September 2023 framework organizes a responsible scaling policy around capability limits, necessary protections, evaluations, response plans and accountability. Its sample language connects specific observations to investigation, access restrictions or a pause, and assigns responsibility for evidence and policy revisions. The value is in making the decision process explicit before a threshold is crossed. This is a historical proposal with illustrative thresholds, not a statement of current developer commitments or a substitute for applicable regulation.

My takeaway: For each trigger, record the test, required protection, decision owner and action deadline. Rehearse the response, retain evidence that the protection works, and version policy changes so a threshold cannot disappear through an undocumented revision.
Keep exploring

More curated notes connected through AI Compliance 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.