AI Engineer · October 30, 2026

Model selection: measure task success and total cost on your own workload

video Model Evaluation AI Engineering

Model selection: measure task success and total cost on your own workload video thumbnail

Why it matters

Rayan Krishnan shows why token prices and overall benchmark ranks can mislead model selection. Task mix, token consumption and the choice between partial credit and fully correct answers change the comparison. He describes replaying historical work and comparing cost against quality. Private savings figures and model rankings are examples, not independently verified results.

My takeaway: Build a held-out set of representative completed tasks with explicit acceptance criteria. Run candidate models with recorded harness settings and repeat trials. Compare total cost per task, full-task success and latency by task family; include retries and hosting costs. Audit traces for unintended model calls, grading shortcuts and answers that satisfy a rubric without solving the user’s problem.

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.