AI Engineer · September 25, 2026

Teaching LLMs to Speak Spotify — Yves Raimond & Jacqueline Wood, Spotify

video AI Engineering Model Evaluation

Teaching LLMs to Speak Spotify — Yves Raimond & Jacqueline Wood, Spotify video thumbnail

Why it matters

Yves Raimond and Jacqueline Wood explain how Spotify connects an LLM to catalog items through semantic IDs. A staged training recipe first grounds new catalog embeddings against a frozen backbone, then adapts the model to recommendation tasks. The talk also covers editable taste profiles, decoding choices and listener-aware judges. Reported evaluation figures lack sufficient dataset detail for a general performance comparison.

My takeaway: Evaluate catalog validity, recommendation relevance, retained language ability and explanation accuracy separately. Ground judges in appropriate user context, and test whether explicit preference corrections change recommendations as intended.

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.