Özge Çinko

Even small changes in LLMs can affect output quality, safety, and user experience. In this talk, we will show how to use Langfuse to log LLM outputs, run A/B tests, and track important metrics.

Large Language Models are rapidly changing how we think about recommendation systems. Traditional pipelines based on collaborative filtering or matrix factorization are being complemented and sometimes replaced by embedding-based and LLM-driven approaches.

Modern AI applications often fail not because models are weak, but because memory is poorly designed. In this talk, I’ll share how to design reliable, time-aware memory layers in Python and what breaks when AI systems remember the wrong things.

Have you ever wondered how Shazam identifies a song in just a few seconds, even in a noisy environment? In this talk, we’ll learn the core technology behind Shazam’s magic: audio fingerprinting.

Even small changes in LLMs can impact output quality, safety, and user experience. In this talk, we’ll show how to log experiments with Langfuse, automate tests with Pytest, and enrich them using Hypothesis-generated random data scenarios. Participants will learn how to use code, tests, and...