📌 How to Ensure Your AI Solution Does What You Expect iI to Do

🗂 Category: ARTIFICIAL INTELLIGENCE

🕒 Date: 2025-04-28 | ⏱️ Read time: 10 min read

A Kind Introduction to AI Evals

📌 Fighting Back Against Attacks in Federated Learning

🗂 Category: MACHINE LEARNING

🕒 Date: 2025-09-10 | ⏱️ Read time: 8 min read

Lessons from a multi-node simulator

📌 When A Difference Actually Makes A Difference

🗂 Category: DATA SCIENCE

🕒 Date: 2025-09-10 | ⏱️ Read time: 10 min read

Bite-Sized Analytics for Business Decision-Makers (1)

📌 Why Task-Based Evaluations Matter

🗂 Category: ARTIFICIAL INTELLIGENCE

🕒 Date: 2025-09-10 | ⏱️ Read time: 4 min read

This article is adapted from a lecture series I gave at Deeplearn 2025: From Prototype…

📌 How to Build an AI Budget-Planning Optimizer for Your 2026 CAPEX Review: LangGraph, FastAPI, and n8n

🗂 Category: ARTIFICIAL INTELLIGENCE

🕒 Date: 2025-09-10 | ⏱️ Read time: 20 min read

Email → n8n → LangGraph → FastAPI: turning budget requests into optimised CAPEX portfolios that…

📌 Struggling to Land a Data Role in 2025? These 5 Tips Will Change That

🗂 Category: DATA SCIENCE

🕒 Date: 2025-04-28 | ⏱️ Read time: 7 min read

Your dream data job isn’t ghosting you—you just need to search smart.

📌 NumExpr: The “Faster than Numpy” Library Most Data Scientists Have Never Used

🗂 Category: PROGRAMMING

🕒 Date: 2025-04-28 | ⏱️ Read time: 8 min read

A comparative performance test with NumPy

📌 When OpenAI Isn’t Always the Answer: Enterprise Risks Behind Wrapper-Based AI Agents

🗂 Category: ARTIFICIAL INTELLIGENCE

🕒 Date: 2025-04-28 | ⏱️ Read time: 8 min read

Data privacy, compliance, and trust gaps in today’s AI agent integrations

📌 Adding Training Noise To Improve Detections In Transformers

🗂 Category: DEEP LEARNING

🕒 Date: 2025-04-28 | ⏱️ Read time: 8 min read

Denoising, explained

📌 Hands-on Multi Agent LLM Restaurant Simulation, with Python and OpenAI

🗂 Category: LARGE LANGUAGE MODELS

🕒 Date: 2025-04-28 | ⏱️ Read time: 12 min read

This is how I used Large Language Models Agents to simulate an end-to-end restaurant process,…

📌 A Step-By-Step Guide To Powering Your Application With LLMs

🗂 Category: LARGE LANGUAGE MODELS

🕒 Date: 2025-04-25 | ⏱️ Read time: 8 min read

Explore a hands-on guide to integrating large language models into real-world apps, not just read…

📌 Behind the Magic: How Tensors Drive Transformers

🗂 Category: LARGE LANGUAGE MODELS

🕒 Date: 2025-04-25 | ⏱️ Read time: 4 min read

The workflow Of tensors Inside Transformers

📌 LLM Evaluations: from Prototype to Production

🗂 Category: ARTIFICIAL INTELLIGENCE

🕒 Date: 2025-04-25 | ⏱️ Read time: 30 min read

How to monitor the quality of your LLM product

📌 AWS: Deploying a FastAPI App on EC2 in Minutes

🗂 Category: DATA ENGINEERING

🕒 Date: 2025-04-24 | ⏱️ Read time: 5 min read

From zero to EC2: easy steps to launching an AWS Instance

📌 Government Funding Graph RAG

🗂 Category: DATA SCIENCE

🕒 Date: 2025-04-24 | ⏱️ Read time: 19 min read

Graph visualisation for UK Research and Innovation (UKRI) funding, including NetworkX, PyVis and LlamaIndex graph…

📌 How to Integrate AI into Complex Workflows

🗂 Category: THE VARIABLE

🕒 Date: 2025-04-24 | ⏱️ Read time: 3 min read

This week, we focus on the nitty-gritty details of integrating AI workflows into new contexts.

📌 Choose the Right One: Evaluating Topic Models for Business Intelligence

🗂 Category: MACHINE LEARNING

🕒 Date: 2025-04-24 | ⏱️ Read time: 11 min read

Python tutorial for evaluating top-notch bigram topic models in customer email classification

📌 Predicting the NBA Champion with Machine Learning

🗂 Category: DATA SCIENCE

🕒 Date: 2025-04-24 | ⏱️ Read time: 10 min read

Building a machine learning model to predict the NBA Champion and analyze the most impactful…

📌 Exporting MLflow Experiments from Restricted HPC Systems

🗂 Category: DATA ENGINEERING

🕒 Date: 2025-04-23 | ⏱️ Read time: 4 min read

A workaround method that bypasses direct communication

📌 How to Benchmark DeepSeek-R1 Distilled Models on GPQA Using Ollama and OpenAI’s simple-evals

🗂 Category: LARGE LANGUAGE MODELS

🕒 Date: 2025-04-23 | ⏱️ Read time: 12 min read

Set up and run the GPQA-Diamond benchmark on DeepSeek-R1’s distilled models locally to evaluate its…

📌 Why Most Cyber Risk Models Fail Before They Begin

🗂 Category: CYBERSECURITY

🕒 Date: 2025-04-23 | ⏱️ Read time: 5 min read

The case for quantitative thinking in cyber risk