Agentic AI from First Principles: Reflection
says that “any sufficiently advanced technology is indistinguishable from magic”. That’s exactly how a lot of today’s AI frameworks feel. ...
Read more
When Transformers Sing: Adapting SpectralKD for Text-Based Knowledge Distillation
While working on my Knowledge Distillation problem for intent classification, I faced a puzzling roadblock. My setup involved a teacher ...
Read more
How to Control a Robot with Python
PyBullet is an open-source simulation platform created by Facebook that’s designed for training physical agents (such as robots) in a ...
Read more
Why Should We Bother with Quantum Computing in ML?
When black cats prowl and pumpkins gleam, may luck be yours on Halloween. (Unknown) , conferences, workshops, articles, and books ...
Read more
Is RAG Dead? The Rise of Context Engineering and Semantic Layers for Agentic AI
Introduction Retrieval-Augmented Generation (RAG) may have been necessary for the first wave of enterprise AI, but it’s quickly evolving into ...
Read more
Scaling Recommender Transformers to a Billion Parameters
! My name is Kirill Khrylchenko, and I lead the RecSys R&D team at Yandex. One of our goals is ...
Read more
How to Build An AI Agent with Function Calling and GPT-5
and Large Language Models (LLMs) Large language models (LLMs) are advanced AI systems built on deep neural network such as transformers ...
Read more
How to Build Guardrails for Effective Agents
increasingly prevalent in a lot of applications. However, integrating agents into your application is a lot more than just giving ...
Read more
Conceptual Frameworks for Data Science Projects
are analytical structures for representing abstract concepts and organizing data. Data scientists regularly use such frameworks — knowingly or unknowingly ...
Read more
Python 3.14 and the End of the GIL
of the most eagerly awaited releases in recent times, is finally here. The reason for this is that several exciting ...
Read more
