Is Ralph Wiggum the Future of Coding?
Autonomous AI coding doesn't fail because models aren't smart enough. It fails because we give them too much context, vague goals, and no hard definition of success. The Ralph Wiggum approach flips that on its head. Short contexts, brutally clear tasks, hard completion signals, and relentless...
The Next AI Breakthrough Is Old-Fashioned Software Engineering
The next AI breakthrough won't be smarter models but reliable ones. Like self-driving cars, progress of AI agents means consistency over demos. The future of AI lies in disciplined software engineering, building agents that work safely and predictably every time, not just sometimes.
The 4 Ways LLMs Fail
Large language models (LLMs) and AI agents that use them often get lauded as magic. But anyone using them in production or serious applications quickly learns how often they fail. What we commonly call hallucinations, workslop, or vulnerabilities are not random bugs. They tend to cluster into...
No, RAG Isn't Dead, It Just Leveled Up As Context Engineering
There’s been a lot of recent buzz around whether Retrieval Augmented Generation (RAG) has reached its limits. Is RAG truly dead or just replaced by new approaches like search agents, MCP, or massive context windows? That's still retrieval-augmented generation under a new name.
LLM Routers - The AI Dispatchers You Didn't Know You Needed
Most AI models aren't generalists—they're specialists. With over 200,000 LLMs available, choosing just one model for your AI product won't cut it. Enter LLM routers - technology that routes each task to the model best suited to handle it. Discover how routers can cut costs by 85%, improve spe...
Building a Perplexity Clone with 100 lines of code
AI search apps like Perplexity.ai are really cool. They use an LLM to answer your questions, but pull in real-time search results to augment the answer (eg RAG) and list citations. I wanted to know how it works and decided to build my own version. Getting it to work is surprisingly simple and...
A Brief History of Scaling Uber
On a cold evening in Paris in 2008, Travis Kalanick and Garrett Camp couldn't get a cab. Fast forward to today where Uber is the largest mobility platform in the world, in over 70 countries, 10,500 cities, and 130 million users. Here's the story of the key moments in scaling Uber engineering ...
Recreating my Site as a 90s Webpage
I revisited the look of early web design by recreating my home page with a 90s theme. Drawing inspiration from iconic sites like Space Jam, I incorporated classic elements such as gif badges, pixelated fonts, and dithered images to capture the era's distinct look.
Using AI Language Models to Generate Fantasy Football Player Outlooks
I explored using OpenAI's gpt-3 language models to generate fantasy football player outlooks for my Draft Punk app. Through experimentation with different models, retrieval-augmented generation, and prompt engineering, I learned how to create compelling, fact-based player narratives that riva...
Think Like a Farmer
You don't grow crops by yelling at plants and you don't grow team velocity by pressuring engineers. Great managers prepare the ground. Give clarity, tools, and trust. Focus on support, not blame. Remove blockers, nurture growth, match people to problems, and improve yourself first.