AI Engineer · November 11, 2026

Nikolay Petrov: evaluate skill instructions before shortening them

Nikolay Petrov: evaluate skill instructions before shortening them video thumbnail
Why it matters

Nikolay Petrov presents a controlled way to determine what a knowledge-oriented agent skill contributes. Break its instructions into small checkable propositions and contracts, write questions that do not disclose their answers, and compare the same model with and without the skill. A separate judge or panel can classify four outcomes: knowledge already present, newly enabled answers, regressions caused by the skill and information still missing in both conditions. He distinguishes broad conceptual understanding from exact parameters and procedural details; a model recognizing the general idea does not establish that detailed instructions are redundant. Knowledge novelty is only a guide to optimization. After removing or revising material, the complete skill must still pass task evaluations, with attention to token use and execution time. The talk explicitly separates knowledge skills from process or steering skills, whose value may lie in consistent behavior even when the underlying information is familiar. Its headline percentage is not a universal deletion target.

My takeaway: Create paired skill/no-skill evaluations for representative tasks and exact-detail questions. Fix instruction-induced regressions first, then trial smaller versions; keep a change only when full workflow behavior and required process constraints remain reliable across the models you deploy.
Keep exploring

More curated notes connected through AI Engineering and Model Evaluation.

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.