Michał Oleszak – Medium

Michał Oleszak

Pinned

About me

Welcome to my Medium page!

Aug 12, 2021

Aug 12, 2021

Published in
Towards Data Science

Reinforcement Learning from Human Feedback (RLHF) for LLMs

An ultimate guide to the crucial technique behind Large Language Models

Sep 23

Reinforcement Learning from Human Feedback (RLHF) for LLMs

Sep 23

Published in
Towards AI

Adversarial Machine Learning: Defense Strategies

Know thine enemy and protect your machine learning systems.

Jul 19

Adversarial Machine Learning: Defense Strategies

Jul 19

Published in
Towards AI

Zero-Shot and Few-Shot Learning with LLMs

Guidelines for optimal use.

Apr 18

Zero-Shot and Few-Shot Learning with LLMs

Apr 18

Published in
Towards Data Science

Designing RAGs

A guide to Retrieval-Augmented Generation design choices.

Mar 14

Designing RAGs

Mar 14

Published in
Towards Data Science

Detecting Concept Shift: Impact on Machine Learning Performance

When should I retrain my model?

Jan 16

Detecting Concept Shift: Impact on Machine Learning Performance

Jan 16

Published in
Towards Data Science

Evaluating Large Language Models

How do you know how good your LLM is? A complete guide.

Jan 14

Evaluating Large Language Models

Jan 14

Published in
Towards AI

Building a Recommender for Implicit Feedback Data

Provide personalized recommendations without knowing your users.

Sep 4, 2023

Building a Recommender for Implicit Feedback Data

Sep 4, 2023

Published in
Towards Data Science

Organizing a Machine Learning Monorepo with Pants

Streamline your ML workflow management

Aug 18, 2023

Organizing a Machine Learning Monorepo with Pants

Aug 18, 2023

Published in
Towards AI

AI Pulse #2: Meta’s Human-Like AI & Small Language Models

Meta’s two new models learn more as humans do, and what do small language models actually learn?

Jul 11, 2023

Jul 11, 2023

Michał Oleszak

Michał Oleszak

ML Engineer & Manager | Top Writer in AI & Statistics | michaloleszak.com | Book 1:1 @ topmate.io/michaloleszak

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams