≥20min
(13)Model architectures, data generation, training paradigms, and unified frameworks inspired by LLMs.
16 Mar 2025  ·  43 min  ·  recsys llm teardown survey
Use cases, techniques, alignment, finetuning, and critiques against LLM-evaluators.
18 Aug 2024  ·  49 min  ·  llm eval production 🔥
What to interview for, how to structure the phone screen, interview loop, and debrief, and a few tips.
07 Jul 2024  ·  21 min  ·  machinelearning career leadership 🔥
Evals for classification, summarization, translation, copyright regurgitation, and toxicity.
31 Mar 2024  ·  33 min  ·  llm eval machinelearning
Overcoming the bottleneck of human annotations in instruction-tuning, preference-tuning, and pretraining.
Reference, context, and preference-based metrics, self-consistency, and catching hallucinations.
Evals, RAG, fine-tuning, caching, guardrails, defensive UX, and collecting user feedback.
30 Jul 2023  ·  66 min  ·  llm engineering production 🔥
9 patterns including HITL, hard mining, reframing, cascade, data flywheel, business rules layer, and more.
23 Apr 2023  ·  20 min  ·  machinelearning engineering production recsys
A whirlwind tour of bandits, embedding+MLP, sequences, graph, and user embeddings.
13 Jun 2021  ·  25 min  ·  teardown recsys machinelearning deeplearning
An overview and comparison of the various approaches, with examples from industry search systems.
25 Apr 2021  ·  21 min  ·  teardown machinelearning production 🔥
Why real-time? How have China & US companies built them? How to design & build an MVP?
10 Jan 2021  ·  21 min  ·  teardown machinelearning recsys production 🔥
Examining the broad strokes of NLP progress and comparing between models
16 Aug 2020  ·  23 min  ·  nlp deeplearning survey
After this article, we'll have a workflow of tests and checks that run automatically with each git push.
21 Jun 2020  ·  20 min  ·  engineering production python productivity 🔥
Join 10,300+ readers getting updates on machine learning, RecSys, LLMs, and engineering.