Most Recent Posts
J-Space: How Anthropic Reads Claude's Silent Thoughts - 9 July 2026
The Dividend Is Not Speed: Steering a Team Through AI Coding Tools - 8 July 2026
Agent Memory: How AI Agents Remember, Forget, and Learn on the Job - 7 July 2026
Goals and Loops: Telling Your Coding Agent When It's Done - 6 July 2026
Working With Coding Agents: Principles for Reliable AI-Built Software - 5 July 2026
How LLMs Scale: FLOPs, Bytes, and the Price of a Token - 5 July 2026
The Evolution of Attention: One Mechanism, Four Escape Routes - 4 July 2026
Knowledge Distillation: How Frontier Intelligence Gets Cheap - 3 July 2026
Diffusion Models: Learning to Create by Learning to Destroy - 2 July 2026
The KV Cache: Why LLMs Never Do the Same Work Twice - 1 July 2026
June 2026
Causal Inference: Answering the Questions Prediction Can't - 29 June 2026
Reasoning Models: Teaching LLMs to Think Before They Answer - 27 June 2026
February 2026
Unlocking Customer Lifetime Value (CLV) with Kaplan-Meier Survival Curves - 20 February 2026
The Geometry of Pricing: How We Turned a Prediction Problem Into a Decision Problem - 5 February 2026
January 2026
Engineering Retention: Interpretable Churn Cohort Discovery for Broadband - 15 January 2026
2025
September 2025
Mixed Effects Models: Partial Pooling for Data That Comes in Groups - 3 September 2025
July 2025
Generalized Linear Models: The Recipe Behind Linear and Logistic Regression - 15 July 2025
February 2025
Building a 'Similar Products' Recommender - A Content-Based Approach - 7 February 2025
Actor-Critic Methods in Reinforcement Learning - An Introduction - 3 February 2025
January 2025
Chatbots in Education - Exploring the Past, Present, and Future of Conversational AI - 23 January 2025
2024
December 2024
Stratified Sampling - A solution to working with large data - 13 December 2024
November 2024
Generative AI Meets Intent Classification - A Smarter Approach - 30 November 2024
Less is More - Reducing Annotation Costs with Active Learning - 24 November 2024
October 2024
Semantic Search for Customer Search Queries - 13 October 2024
Finetuning LLMs - LoRA - 6 October 2024
June 2024
Detecting Statistical Differences in Feature Distributions - 24 June 2024
Exploration into Kolmogorov Arnold Networks - 9 June 2024
May 2024
Aligning Multi-Armed Bandits for Dynamic Optimization of Customer Assignments in Recommendation Models - 30 May 2024
2023
November 2023
Langchain - Bigquery SQL agent - 19 November 2023
September 2023
Unpacking Docker - An Exploration Under the Hood - 28 September 2023
A Beginner's Guide to Policy Gradients in Reinforcement Learning - 10 September 2023
Understanding & Utilising Langchain - 2 September 2023
August 2023
HuggingFace - NLP playaround - 26 August 2023
Language, Learning, and AI - An Exploration of Large Language Models - 9 August 2023
Autoencoders Explained - Breathing Life into Data - 2 August 2023
July 2023
Transfer Learning: Reusing Pre-trained Layers - 25 July 2023
Recommender Sytems - Learning To Rank - 24 July 2023
I want AI/ML! Do you need it though... - 22 July 2023
June 2023
Understanding Sampling - 23 June 2023
XGBoost, Understanding Tuning - 17 June 2023
May 2023
ChatGPT, what exactly is the hype? Exploring the innner workings.... - 28 May 2023
Target Encoding, the secret to making better features! - 20 May 2023
Method Chaining (Flow Programming), making analysis neater! - 19 May 2023
January 2023
Intro to world of Recommender Systems - Collaborative Filtering - 17 January 2023