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 10, 2026

SWE-bench test passes do not establish that maintainers would merge a patch

analysis Model EvaluationAI Engineering
Why it matters

METR asked maintainers from three SWE-bench Verified repositories to review agent-generated patches and compared their decisions with the automated grader. Many test-passing patches still failed on functionality, regressions or code quality, even after adjusting for inconsistent acceptance of historical human patches. The study covers older models, one harness and static submissions without iterative feedback. It supports a gap between benchmark acceptance and maintainer judgment, not a permanent ceiling on agent capability.

My takeaway: Add repository-aware review and realistic acceptance criteria to coding-agent evaluations. Measure revisions needed to reach a mergeable result, rather than treating a test pass as completion. Disclose reviewer noise, missing CI and whether agents had a chance to respond to feedback.
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.