Technical notes, project documentation, and lessons learned across software, DIY, writing, and more.
We had architecture documents, code smell guides, testing strategies, and a global AI instructions file with every lesson learned. We found 34 bugs in one audit. This is what happens after 'it works.'
Someone dropped the classic comment under my Tailwind post. It's the same false choice that shows up with every new tool: ORMs vs SQL, TypeScript vs JavaScript, AI vs coding. The premise — that using modern tools means you skipped the fundamentals — is almost always backwards.
ChatGPT will not write your novel for you. After months of trying, here's what AI actually does well for fiction—and where it fails catastrophically.
Part 2 of the SMS AI series. RAG transforms generic AI into useful AI. Here's how I added vector search, conversation memory, and production resilience.
Can I text an AI instead of opening another app? Turns out yes—and it validates a compelling business model. Here's how I built SMS-to-custom-LLM in ~40 lines of code.
In which the author documents humanity's imminent obsolescence at the hands of our mechanical overlords. (Or does he?)
LinkedIn hot takes say AI replaces coders. After a year building production apps with AI assistance, here's what actually happens - and why expertise still matters.
I built a Discord bot to summarize hundreds of messages using OpenAI - then discovered that all Discord bots run as a single instance serving every server. Here's the journey.
I exported two years of AI chats and used embeddings, clustering, and topic segmentation to find patterns. Here's what I learned - explained so anyone can understand.
I asked two AIs to help debug performance issues. One maintained context and found the root cause. The other kept saying 'likely your code does this' while looking at the actual code.