ML & AI in Action

Practical insights on machine learning, AI systems, and building products that ship. Topics include RLHF, LLM optimization, recommender systems, and generative UI.

Topic Hubs

• LLM Agents

  Tool use, agent runtime design, evaluation, context, and production patterns for systems that act across tools and environments.

• Evaluation

  Practical approaches to measuring model and agent capability with deterministic checks, rubrics, trajectories, and verifiable outcomes.

• Post-Training

  SFT, RLHF, preference optimization, instruction following, reasoning traces, and data pipelines for shaping model behavior after pretraining.

• RLHF and Preference Optimization

  Engineering notes and research synthesis on PPO, DPO, GRPO, reward modeling, preference data, and model behavior optimization.

• Generative UI

  How AI systems can produce, steer, and execute user interfaces with structured representations and practical product constraints.

Featured

• How to Arbitrarily Increase the Difficulty of Agent Evaluation Sets

  28 May, 2026 · 18 min read

  A practical framework for making agent benchmarks harder in a controlled way: treat difficulty as trajectory-graph complexity, not prompt wording. Covers deterministic scoring, capability facets, harness effects, and systematic data generation.

• The Mercor Breach: What 4TB of Stolen Data Reveals About How Frontier AI Labs Actually Train Models

  12 Apr, 2026 · 22 min read

  A $10B AI data vendor was breached, exposing 84 Airtable workspaces of training data for OpenAI, Anthropic, Apple, Amazon, and Meta. This post analyzes what the public reporting reveals about each lab's evaluation methodology — rubric design, RLHF pipelines, and quality control — and what it means for the industry.

• Improving LLM Internationalization: Bridging the Gap in Tool Use and Agency

  10 Mar, 2026 · 17 min read

  LLMs achieve 57% tool-calling accuracy in English but only 34% across 52 languages — and 6.8% for the worst. This post covers the full playbook for closing the multilingual gap: training-time techniques, agentic architecture patterns, failure mode analysis, and RL-based approaches for i18n.

• The Unverifiable Reward Problem: The Real Frontier of RL for LLMs

  7 Mar, 2026 · 11 min read

  Deep research on tasks with unverifiable rewards in RL — the key bottleneck for scaling RL beyond math and code. Covers JEPO, NRT, RLNVR, self-play methods, GenRM, Constitutional AI, reward hacking mitigation, and more.

• Instruction Following: What Models Get Wrong and How to Fix It with Better Post-Training Data

  4 Mar, 2026 · 36 min read

  LLMs can write poetry and solve math, but ask them to 'respond in exactly 3 bullet points using only lowercase' and they stumble. This post dissects the taxonomy of instruction-following failures and provides a practical playbook for building post-training data that actually fixes them.

• Experience-Augmented In-Context Learning: A Training-Free Complement to RL Post-Training

  28 Feb, 2026 · 23 min read

  RL post-training makes models smarter, but it can't cover the infinite long tail of real-world cases. Experience-augmented ICL retrieves successful reasoning traces at inference time, letting agents learn continuously from real usage — no retraining required.

• Tool Selection Optimization for LLM Agents at Scale

  9 Jan, 2026 · 18 min read

  A deep technical dive into tool selection—retrieval strategies, context optimization, learned selection, and the engineering trade-offs that matter when scaling to hundreds of tools.

• Generative Engine Optimization (GEO): How to Get Your Product Cited by AI

  2 Jan, 2026 · 13 min read

  A comprehensive guide to Generative Engine Optimization—making your content retrievable, citable, and recommendable by large language models.

• Generative UI Doesn't Move the Needle—Steering Does

  31 Dec, 2025 · 10 min read

  After shipping multiple generative UI features, I've concluded that the sophistication of AI-generated interfaces often doesn't translate to user benefit—but steering does.

• RLHF from an Engineering Perspective: PPO, GRPO, DPO, and Tool-Use Implementation

  30 Dec, 2025 · 12 min read

  A practical engineering guide to RLHF implementation—covering PPO, GRPO, DPO, and tool-use training with code snippets and debugging tips.

• Post-Training Is Not 'One Algorithm': Objective Functions and Implementation Essentials for PPO / DPO / GRPO

  30 Dec, 2025 · 12 min read

  Reading notes on RLHF covering PPO, DPO, and GRPO—understanding post-training as an engineering pipeline rather than a single algorithm.

Recent Posts

• Ad Formats in LLM Products: What's Live vs. What's Research

  1 Jan, 2026 · 7 min read

  A survey of advertising formats in LLM products—separating what's deployed in production from what remains in research.

• Adding Ads in LLM/Chatbot: Character Training for Monetization

  1 Jan, 2026 · 4 min read

  Exploring how to integrate ads in LLMs through character training—making recommendations genuinely helpful rather than annoyingly promotional.

• What Worked (and What Didn't) When Training AEs and VAEs for Embedding Compression

  6 Sep, 2025 · 4 min read

  Practical lessons from training autoencoders and VAEs for embedding compression—covering dimension choice, KL scheduling, contrastive signals, and evaluation metrics.

• User Interest Modeling with Transformer Architectures

  6 Sep, 2025 · 4 min read

  Exploring position embeddings, architecture choices, and training techniques for Transformer-based recommender systems.

• UI Representation and Action Execution for Generative UI

  2 May, 2025 · 3 min read

  Exploring structured UI representation using JSON Schema, and how to implement action handlers for generative UI systems.

• A Path Towards Generative UI

  31 Mar, 2025 · 10 min read

  Exploring how LLMs can dynamically generate user interfaces that adapt in real time to user needs—the vision behind generative UI.