AI Learning Guide

This is less a curriculum than a pile of notes I keep nearby — the pieces I wish I’d had in one place when I was first getting a footing, and a few later ones I still go back to.

Start here

AI Beginner's Guide: Learning Artificial Intelligence from Scratch

· 7-10 min read

Artificial Intelligence (AI) is one of the most exciting technology fields today. This article will provide you with a comprehensive guide to getting started with AI.

Ranking and recommendation

Classic Foundational Papers on Ranking & Recommendation Systems

· 15-20 min read

Ranking and recommendation systems power everything from Google Search to Netflix suggestions. While today’s systems use deep learning and large language models (LLMs), their foundations were laid decades...

Deep Learning Era of Ranking & Recommendation Systems: Must-Read Papers (2016–2020)

· 15-25 min read

Explore how deep learning transformed ranking and recommendation systems, from Wide & Deep to BERT4Rec, covering core technologies powering platforms like YouTube, Facebook, and Amazon

Sequential Learning in Recommendation Systems: From Markov Chains to Transformers

· 20-30 min read

A comprehensive guide to sequence-based recommendation techniques and key research papers, tracing the evolution from early statistical methods to modern transformer-based architectures

Contemporary RecSys: Industry-Scale Architectures & Multimodal Systems (2020–2025)

· 15-25 min read

This era represents a pivotal shift toward production-ready, billion-scale architectures that power today’s major platforms. This comprehensive guide covers the essential papers that define contemporary RecSys, from industry-standard...

Modeling Long User Histories for Ads Ranking

· 20-30 min read

How ads ranking systems went from aggregated feature counts to retrieve-and-compress architectures that handle 10,000+ user events under millisecond latency constraints.

Language models and reasoning

Reasoning in Large Language Models: A Research-Centric Overview

· 15-25 min read

“Can LLMs reason?” is one of those questions that generates more heat than light, mostly because people mean very different things by “reasoning.” This post tries to cut...

Training signals, reward, and alignment

The Evolution of Reward Hacking and Jailbreak Research in AI

· 25-30 min read

From specification gaming in classical RL to deceptive alignment and jailbreaks in LLMs—a survey of how reward hacking has become a central challenge in AI safety and alignment....

Why Final-Outcome Rewards Are Not Enough for AI Agents

· 15-18 min read

An outcome reward tells you whether a trajectory worked. It doesn't say why. I think the interesting question is whether the process rewards we train on today measure...

More to come.

Adjacent: Paper Readings · Research Blog