AI Engineer · October 4, 2026

Choose prompts, retrieval and fine-tuning according to the failure you need to fix

video AI Engineering Prompt Engineering Model Evaluation

Choose prompts, retrieval and fine-tuning according to the failure you need to fix video thumbnail

Why it matters

Anant Srivastava separates stable behavioral instructions, changing factual knowledge and learned task behavior. His examples show how training on historical support tickets can preserve obsolete product facts even after a prompt update, while fine-tuning on runbooks leaves missing-document retrieval unresolved. He proposes code-aware chunking and permission metadata for retrieval, and fine-tuning only after human judgments converge on a stable task. This is an architectural diagnostic, not a measured comparison proving one storage choice always wins.

My takeaway: Trace a wrong answer to the instructions, retrieved evidence or learned behavior that produced it. Test retrieval permissions and freshness before training, and retain human review for disputed labels and drifting decisions.

Keep exploring

More curated notes connected through AI Engineering and Prompt 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.