THE JOURNAL
Archive
Not ordered by popularity—only by the day each note was written.
2026
- Evaluating RAG Beyond Plausible AnswersAI Engineering
- Agents Need Explainable Traces, Not Just More LogsAI Engineering
- Why Better Offline Ranking Does Not Guarantee Better Online ResultsRecommender Systems
- Why This Blog Exists: A Version History for Technical GrowthLearning & Career
- Reading Transformer: Why Attention Could Replace RecurrencePaper Notes
- Write the Learning Process, Not Only the Model ConclusionAI Engineering
- Keep a Ledger for Every ExperimentEngineering Practice
- Reading DeepFM: Learning Low- and High-Order Feature Interactions TogetherPaper Notes
- How Deep Should I Learn a New Technology?Learning & Career
- What a Recommender-Model Experiment Should Leave BehindEngineering Practice
- Reading ESMM: Modeling Post-Click Conversion in the Entire SpacePaper Notes
- Reading ReAct: Closing the Loop Between Reasoning and ActionPaper Notes
- Leave a Table for an Unfinished Agent IdeaAI Engineering