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 21, 2026

Expenditure Horizon: Measuring Optimization Ability, with an Application to NanoGPT

framework Model EvaluationAI EngineeringAgent Security
Why it matters

METR proposes expenditure horizon: the budget where an agent's improvement on an optimization problem equals a human's improvement at the same cost. Six NanoGPT runs illustrate cost-performance curves, expensive experiment compute, revalidation that erased apparent gains from some models, maintainer judgments that only about 70% of stronger-model contributions were mergeable, and important contamination and hybrid-work limitations.

My takeaway: For optimization-agent evaluations, report the complete cost-performance curve, include token, experiment, and human-review costs, independently re-run the best artifacts, and have domain maintainers judge mergeability. Disclose harness inefficiency, task contamination, noisy metrics, and the gap between autonomous and human-agent performance before claiming R&D acceleration.
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.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

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.