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 · March 20, 2026

Time-horizon estimates: test sensitivity to tasks, curve fits and human timing

analysis Model Evaluation
Why it matters

METR’s March analysis shows how statistical choices affect estimates of the task duration at which agents achieve a specified success rate. It examines a regularization correction, alternative success curves, public-task inclusion and noise in human completion-time estimates. Reasonable alternatives often move the point estimates within already wide confidence intervals. Task distribution remains the author’s largest uncertainty, especially as capable models approach the end of a suite with few long tasks.

My takeaway: Report uncertainty and the task distribution alongside any time-horizon point estimate. Refit with reasonable alternative assumptions, distinguish measured human baselines from estimated task lengths, and compare public-only effects without treating them as proof of contamination. Keep 50% and 80% reliability thresholds explicit.
Keep exploring

More curated notes connected through 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.