LLM

I recently removed a vector database from a few parts of my software. Not because vector databases are bad. Not because embeddings stopped being useful. And definitely not because I suddenly decided that AI infrastructure is overhyped. The reason was much more boring: I was using the wrong tool for some of the jobs. One of those jobs was source-code retrieval for RAG. The original version worked the way most first versions work: split the repository into chunks, embed each chunk, store the embeddings, and retrieve the chunks that looked closest to the user’s query....

There’s an agent design pattern with an uncomfortable premise: the agent is the orchestrator, and you are one of its tools. It goes by a few names — human-as-a-tool, human-as-tool, sometimes lumped under “human-in-the-loop.” But it’s worth separating the two, because the inversion is the whole point. Human-in-the-loop vs. human-as-a-tool Human-in-the-loop keeps the human in charge. The agent proposes, the human approves. You’re the supervisor signing off on the intern’s work before it ships....

When you run a team, you don’t decide who to keep based on their resume from two years ago. You watch what they actually ship on your work, and you promote the ones who deliver and let go of the ones who don’t. I want the same thing for the models I use as agents. And public leaderboards don’t give it to me. Why public benchmarks don’t tell you what you need A leaderboard tells you how a model did on someone else’s tasks, scored on someone else’s rubric, often on problems that leaked into training data....

When I’m in AI Studio mode (rapid prototyping, lots of experiments), I want to spend my time on prompts, evals and breaking the code — not on re-learning yet another SDK. That’s why I use aisuite for most of my AI projects: One client API across providers Switching models is usually just changing a string like openai:gpt-5-mini → minimax:MiniMax-M2.1-lightning or even local ollama It stays close to the OpenAI-style shape, so it’s easy to adopt Lately I use quite a bit Minimax for coding tasks because it hits a great ratio of price vs quality....

Running local LLMs is kinda addictive. New model drops? Gotta try it. But here’s the thing—you need a quick way to check if a model’s actually thinking or just spitting out vibes. The Prompt Here’s my go-to sanity check: What is the number that rhymes with the word we use to describe a tall plant? That’s it. Dead simple. Why This Works It’s not about being hard. It’s about being consistent....

Large Language Models are superuseful right, but they have a well-known weakness: hallucinations. These are confident-sounding responses that are factually incorrect or completely fabricated. While no technique eliminates hallucinations entirely, these three strategies significantly reduce their occurrence in production systems. 1. Provide an Escape Hatch One of the most effective ways to reduce hallucinations is giving the model permission to admit uncertainty. LLMs are trained to be helpful, which sometimes leads them to generate plausible-sounding answers even when they lack sufficient information....