Using Jev to verify cached LLM answers
Originally published on samuelagbede.com. Could Jev help reduce LLM costs by checking when a cached answer can be reused? I wrote about the basics and...
How Does the Dot Product Measure Similarity?
Originally published on samuelagbede.com. I was studying Build a Large Language Model (From Scratch) the other day when I came across the idea of using dot...
How LLMs Turn Text into Embeddings
Originally published on samuelagbede.com. This is part of my learning to build LLMs from scratch. I am following Sebastian Raschka's Build a Large Language...
Designing AI Agents from the Outside In
Originally published on samuelagbede.com. “A problem well stated is a problem half-solved.” Often attributed to Charles F. Kettering I like the PEAS...
Could agents learn to work better from their own runs?
Originally published on samuelagbede.com. What if agents studied their own past runs to do future ones more efficiently? Agent memory has become a major...
Context engineering needs a context engine
Originally published on samuelagbede.com. One of my highlights from last week was speaking at WeAreDevelopers about context engineering. My argument was...
Borrowed confidence is fragile in agentic systems
Originally published on samuelagbede.com. How do you know that your agentic system does what you mean for it to do? And how do you know that the tools you...
The lethal trifecta in AI agents
Originally published on samuelagbede.com. Imagine you're building an AI agent. You give it access to your files, your conversations, and your credentials....
How Plan Caching Reduces LLM Agent Costs
Originally published on samuelagbede.com. Every time your agent tackles a new task, it plans from scratch. Even when it has solved the same kind of problem a...
Stop filling your agent's context window just because you can
Originally published on samuelagbede.com. Stop filling your agent's context window just because you can. A few months ago, I worked on a browser agent which...
I benchmarked 5 embedding models across 4 datasets
Originally published on samuelagbede.com. Bigger embeddings = better retrieval. That has always been my assumption, until I decided to test it. I benchmarked...
Why reranking matters with cross-encoders
Originally published on samuelagbede.com. I was reading about vector retrieval the other week and came across cross-encoders. I found it genuinely...
A beginner-friendly guide to the GGUF model format
Originally published on samuelagbede.com. Just a few years ago, running a large language model on your laptop sounded impossible. These models lived in...
Semantic Caching in Production
Originally published on samuelagbede.com. If you're running an LLM in production, you've probably seen this in your logs and in your bill: Users ask the same...
