Writing Effective Skills: Best Practices for Agent Onboarding
How to write skills that trigger reliably, load efficiently, and stay maintainable, with concrete examples from official docs, the open specification, and public skill repositories.
Blog
Thoughts on ML models, AI applications, distributed systems, and data platforms.
Understand Reasoning Engine: RL Infrastructure for LLMs, From Algorithms to Production
A deep dive into RL infrastructure for LLMs, from RLHF to RLVR to Agentic RL, with head-to-head experiments comparing rule-based vs. LLM-as-a-Judge rewards and sync vs. async training on SkyRL.
Context Engineering: Managing the Scarcest Resource in Agent Systems
How independently-built agent systems converged on the same architecture for managing finite context windows.
Embracing Functional Architecture in Agent Engineering
How functional architecture helps with durability, security, scalability, and maintainability in agent systems.
From PPO to GRPO: The Evolution of Fine-Tuning for Reasoning Models
From PPO to GRPO: tracing the evolution of policy optimization algorithms for efficient LLM alignment and comparing their real-world applications.
The Recommender's Lesson: How Scalable Learning Augments Human Insight
From collaborative filtering to generative AI: tracing the evolution of recommender systems through the lens of the bitter lesson
Arc-Graph: Declarative Machine Learning for the Age of AI Agents
How declarative ML creates a shared language for human-agent collaboration.
DeepSeek V3 and R1: Innovative Architectures and Advanced Reasoning Capabilities in Open-Source LLMs
A comprehensive analysis of DeepSeek V3 and R1 models, covering key innovations like MLA, MoE, MTP, GRPO, and the evolution from base models to reasoning-capable systems.
Subscribe to updates
Get notified when we publish new articles about ML models, AI applications, and data platforms.