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 · July 10, 2025

A 2025 randomized study found AI slowed experienced maintainers on familiar repositories

analysis Model EvaluationAI Engineering
Why it matters

METR’s early-2025 experiment randomized AI access across 246 real issues completed by 16 experienced open-source developers in repositories they knew well. With the tools available then, mainly Cursor with Claude 3.5 and 3.7 Sonnet, AI access increased completion time by 19%, despite participants believing it had accelerated them. The result concerns this sample, workflow and historical toolset; it does not measure novice programmers, unfamiliar projects or current models. The source now explicitly marks the findings as dated. Random assignment and observed completion time make the study useful as an evaluation design.

My takeaway: Measure assistance with randomized access on representative work, recording actual completion and review time. Compare those measurements with perceived productivity and rerun the experiment when tools or task distributions change.
Keep exploring

More curated notes connected through Model Evaluation and AI Engineering.

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.