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 15, 2024

Capability elicitation: document harness fixes without hiding failed runs

guide Model EvaluationAI Engineering
Why it matters

METR’s March 2024 guidance distinguishes apparent failures caused by infrastructure or tool problems from failures that reveal a capability limit, while recognizing cases where the distinction depends on the intended deployment. It recommends improving an agent on development tasks and inspecting traces before interpreting evaluation results. The proposed failure taxonomy had not been empirically validated at publication. Correcting a setup bug can improve measurement, but supplying task-specific help during a held-out run changes what that result measures.

My takeaway: Keep the original trace and score when investigating a failure. Record every harness patch, human hint and rerun, then report corrected results separately from unassisted attempts. Require evidence before attributing an unexpectedly strong result to benchmark memorization.
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.