Blog
Thoughts on AI, engineering, and building the future.
Do the Simplest Thing: Agent Design for Better Models
Anthropic's 'do the simplest thing that works' guidance applied to building agents that stay simple, observable, and ready for stronger models.
Why Fast, Small Models Are the Way to Go
LLMs fail. The question is not whether your model will fail, but how gracefully and how quickly. Fast failures beat slow failures every time.
Why Open-Weight Models Matter for AI Independence
Why owning open-weight models protects builders from account bans, rate limits, and centralized policy shifts that can kneecap innovation overnight.
The Anti-Slop Backlash: Keep Thinking in a Synthetic Sludge Age
A call to resist automated brain rot, expose the hollow economics of generative visuals, and double down on language-first tools that sharpen judgment.
Why Agentic Search is Replacing Traditional RAG
The AI landscape is witnessing a fundamental shift from static retrieval-augmented generation to dynamic, intelligent search systems. Discover why agentic search represents the future of AI-powered information retrieval.
Why AI Agents Signal the End of Click-Based Computing
How modern AI agents herald a fundamental shift from traditional graphical interfaces to conversational, intent-based interactions that will reshape how we interact with computers.
How Large Language Models Think and Learn
A deep dive into the fascinating mechanisms that enable LLMs to process information, reason, and generate responses - from extended context and in-context learning to the architecture of thought.
The Next Generation of AI Coding Assistants
A comprehensive look at Anthropic's announcement of Claude Opus 4 and Claude Sonnet 4, featuring revolutionary advances in coding capabilities, extended thinking with tool use, and the general availability of Claude Code.
Connecting LLMs to Your Data
A deep dive into Model Context Protocol resources - how they enable LLMs to access external data sources while maintaining application control.
Building the Future of Interactive AI Systems
An in-depth exploration of OpenAI's Agents SDK, its key features, and how it's revolutionizing the development of autonomous AI systems.
MCP and Cursor
Extending AI capabilities with Model Context Protocol, a powerful open standard for connecting Cursor to external tools and data sources.
Chain of Thought Reranking
A technique to optimize LLM responses by extracting and refining their internal reasoning chains.
Building langchain-salesforce
A journey in creating a seamless integration between LangChain's powerful LLM framework and Salesforce's robust CRM platform.
Entropy-Based Chain of Thought Injection
A technique to optimize LLM responses by extracting and refining their internal reasoning chains.
NumPy MCP Server
Building a Model Context Protocol server for numerical computations with NumPy, enabling LLMs to perform mathematical operations.
Building Halcyon-1B: A Creative Writing Model
A venture into developing a specialized language model for creative writing, built on Gemma-3B and fine-tuned for storytelling and narrative construction.