Archive

2026

• Mar 29 Two Bets on Generative Recommendation: Semantic IDs vs. Fine-Tuned LLMs
• Mar 28 The Attention Bottleneck: How Modern LLMs Solved a Problem That Nearly Broke the Transformer
• Mar 25 The Harness Is the Moat: Why Autonomous AI Agents Live or Die by Their Architecture
• Mar 23 Generative Recommendation in Production: HSTU, OneRec, and What Every Major Platform Is Building
• Mar 23 From Vibe Coding to Harness Engineering: How to Actually Ship AI-Assisted Software
• Mar 1 Why LLM Inference Costs Will Keep Falling