AI Engineer · September 21, 2026

Skill engineering: independent reviews, edit hooks and rule-level evaluations

video AI Engineering Model Evaluation Prompt Engineering

Skill engineering: independent reviews, edit hooks and rule-level evaluations video thumbnail

Why it matters

AI Engineer’s notes from Paul Bakaus’s workshop explain separate visual and deterministic reviews, selective instruction loading, edit hooks and rule-by-rule ablation tests. They distinguish blocking pre-tool hooks from post-edit feedback, describe portability failures, and retain human judgment because aesthetic evaluators can reward the wrong behavior.

My takeaway: Separate subjective review from deterministic checks. Test that hooks actually run in each supported harness, provide explicit exceptions for false positives, and remove individual rules during evaluation to check their effect. A logged checklist is evidence of a step, not enforcement of the action boundary.

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.