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 19, 2025

METR’s time-horizon method ties agent success to human task duration

analysis Model Evaluation
Why it matters

METR’s March 2025 research measures how agent success varies with the time human experts need to complete software and reasoning tasks. A fitted success curve yields a horizon at a chosen reliability level, while hierarchical resampling estimates uncertainty across task families, tasks and attempts. The original paper also extrapolated historical growth, but that forecast depends on the trend continuing and on transfer beyond the measured tasks. The source distinguishes its dated static results from a live chart. A 50% horizon describes a success threshold, not dependable execution of a project of that duration.

My takeaway: Choose a reliability threshold appropriate to the workflow and report it with the task distribution and uncertainty. Keep measured horizons separate from extrapolated dates and from the agent’s own runtime.
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.