📌 I Replaced GPT-4 with a Local SLM and My CI/CD Pipeline Stopped Failing

🗂 Category: MACHINE LEARNING

🕒 Date: 2026-04-21 | ⏱️ Read time: 13 min read

The hidden cost of probabilistic outputs in systems that demand reliability

#DataScience #AI #Python

📌 Your RAG Gets Confidently Wrong as Memory Grows – I Built the Memory Layer That Stops It

🗂 Category: LARGE LANGUAGE MODELS

🕒 Date: 2026-04-21 | ⏱️ Read time: 15 min read

As memory grows in RAG systems, accuracy quietly drops while confidence rises — creating a…

#DataScience #AI #Python

📌 Using Causal Inference to Estimate the Impact of Tube Strikes on Cycling Usage in London

🗂 Category: DATA SCIENCE

🕒 Date: 2026-04-22 | ⏱️ Read time: 19 min read

Turning free-to-use data into a hypothesis-ready dataset

#DataScience #AI #Python

📌 Correlation vs. Causation: Measuring True Impact with Propensity Score Matching

🗂 Category: DATA SCIENCE

🕒 Date: 2026-04-22 | ⏱️ Read time: 12 min read

Learn how Propensity Score Matching uncovers true causality in observational data. By finding “statistical twins,”…

#DataScience #AI #Python

📌 From Ad Hoc Prompting to Repeatable AI Workflows with Claude Code Skills

🗂 Category: AGENTIC AI

🕒 Date: 2026-04-22 | ⏱️ Read time: 8 min read

How I turned LLM persona interviews into a repeatable customer research workflow

#DataScience #AI #Python

📌 Ivory Tower Notes: The Methodology

🗂 Category: DATA SCIENCE

🕒 Date: 2026-04-22 | ⏱️ Read time: 6 min read

A short intro to scientific methodology to combat “prompt in, slop out”

#DataScience #AI #Python

📌 How to Run OpenClaw with Open-Source Models

🗂 Category: LARGE LANGUAGE MODELS

🕒 Date: 2026-04-22 | ⏱️ Read time: 8 min read

Run OpenClaw assistant through alternative LLMs

#DataScience #AI #Python

📌 Using a Local LLM as a Zero-Shot Classifier

🗂 Category: LARGE LANGUAGE MODELS

🕒 Date: 2026-04-23 | ⏱️ Read time: 8 min read

A practical pipeline for classifying messy free-text data into meaningful categories using a locally hosted…

#DataScience #AI #Python

📌 I Simulated an International Supply Chain and Let OpenClaw Monitor It

🗂 Category: AGENTIC AI

🕒 Date: 2026-04-23 | ⏱️ Read time: 9 min read

Mario asked me why 18% of his shipments were late when every team hit their…

#DataScience #AI #Python

📌 Your Synthetic Data Passed Every Test and Still Broke Your Model

🗂 Category: DATA SCIENCE

🕒 Date: 2026-04-23 | ⏱️ Read time: 11 min read

The silent gaps in synthetic data that only show up when your model is already…

#DataScience #AI #Python