The Tool Call ProblemOne of the things I spend a lot of time thinking about at work is what happens when an AI assistant decides to call a tool it should not, or calls the right tool with the wrong arguments. The assistanJul 30 · 9 min readbitsofwisdom.hashnode.dev
Version Everything: The ML Practice a Lot of Projects SkipA long time ago, I was working on a model and doing what most people do early on: iterating fast, making transformations directly on the dataset to try to improve results, retraining, checking metricsJul 25 · 6 min readbitsofwisdom.hashnode.dev
Building Arishem: A Multi-Agent System That Tries to Hack Your AI App AI agents are everywhere right now. They read emails, write code, and make decisions on your behalf. I use them a lot, for work and for side projects. And the more I use them the more one question kepJul 21 · 4 min readbitsofwisdom.hashnode.dev
We Built a Nigerian Language Search Model That Beat the State of the Art.I have been building RAG systems for a while now. One thing that kept coming up was how existing embedding models can have real deficiencies when it comes to Nigerian languages. To give you a sense ofJul 11 · 6 min readbitsofwisdom.hashnode.dev
LLM Systems in Production: Evaluating LLM Applications with DeepEvalI work at LaunchpadNG where we're building an AI-powered website builder. The assistant at the core of it can generate full websites, manage inventory, handle bookings and a lot more, all from a chat Jun 26 · 6 min readbitsofwisdom.hashnode.dev
