Tag: #LLM

Go beyond traditional metrics. Master semantic observability to ensure reliability and detect hallucinations in your production RAG systems.

Facing tedious CS exams, I built an AI app in 8 months to automate studying and pseudocode generation. This post details the FastAPI, LLM, and MongoDB architecture.

Explore how active inference enables AI agents to develop curiosity intrinsically, boosting performance from 48% to 100% in foraging tasks. I'll break down the architecture.

I nearly shipped a RAG pipeline with subtle, critical flaws. An evaluation harness caught two major bugs no unit test could ever detect, proving its worth on day one.

Proprietary LLM observability tools often carry a hefty subscription fee. I'll show you how I built an open-source alternative to gain deep visibility into your LLM interactions.

I nearly added an em-dash remover to my LLM library. Learn how testing local models revealed unexpected output patterns and reshaped text preprocessing.

I almost added an em-dash remover to my LLM library, llmclean, based on a faulty assumption. Testing five local models revealed surprising output patterns.