One of the things I've noticed when talking to people about local voice assistants is that we tend to focus on the wrong metrics. We compare model benchmarks. We debate which speech-to-text engine is more accurate. We argue over whether a particular language model is smarter than another. We obsess…
In the first post, I covered the initial architecture for building a production Django RAG chatbot without turning it into an expensive science project. The first version used a straightforward retrieval path: embed the user’s question, search PostgreSQL with pgvector, pass the retrieved context to the LLM, and log enough…
If you spend enough time in local AI communities, it's easy to come away with the impression that you've discovered a loophole. Run models on your own hardware, and you'll avoid subscription fees. Keep your data private. Stop worrying about token limits and API pricing. Take back control from large…
Over the past year or two, I've had more conversations than I can count about AI and what it means for the future of work. Somewhere along the way, the conversation almost always shifts to content creation. "Why would anyone still write blogs?" It's a reasonable question. AI can generate…
Everyone wants to add AI to their products right now. Very few teams stop to ask whether they can actually support it once the proof of concept is over. Can we afford it? Can we observe it? Can we control costs? Can we prevent abuse? Can we improve it over…