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 3, 2026

Playable agent demos need deeper inspection and explicit acceptance criteria

analysis Model EvaluationAI Engineering
Why it matters

A METR researcher tested Opus 4.6 on simplified terminal reimplementations of two existing games. Initial playthroughs found recognizable gameplay alongside missing or broken mechanics, without a predefined scoring rubric. A July follow-up uncovered additional problems that the original inspection missed. The tasks benefited from documented rules and reduced scope, and more complete versions failed on initial attempts. This is a qualitative study of deliverable inspection, not a measure of general game-development productivity.

My takeaway: Define required behavior and excluded scope before evaluation. Test interactions and uncommon states beyond the happy path, then revisit apparently successful deliverables with a domain expert. Record reruns and specification changes, and avoid converting rough human effort estimates into measured productivity gains.
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.