Syed's Blog

114 posts · blog home · terminal version · RSS

Gradient Descent Is Just Walking Downhill Blindfolded

· machine-learning

The algorithm behind almost every neural network, explained with a foggy hill, a careful hiker and a learning rate that's either too shy or too brave.

Overfitting: When Your Model Memorised the Exam Answers

· machine-learning

A model that's perfect on training data and useless on new data is the classmate who memorised last year's paper. Here's how to spot it and fix it.

Small Models, Big Energy: When You Don't Need a Giant Hammer

· ai

The biggest model isn't always the best choice. For many real tasks, a small model is cheaper, faster, private and good enough.

The Ethics Talk Nobody Wants at Standup

· ai

Bias, privacy and accountability aren't philosophy-department problems. They're engineering decisions you're already making, whether you notice or not.

Evaluating LLMs Without Fooling Yourself

· ai

"It looked good when I tried three examples" is not an evaluation. A practical guide to building a small, honest test set for your AI feature.

Tokens, Context Windows and Why the Model Forgot Your Name

· ai

What a token is, why long conversations go weird, and why the model that remembered your project details an hour ago now calls you "the user."

Will AI Take My Job? A Calm, Mildly Sarcastic Analysis

· ai

AI replaces tasks before it replaces jobs. Here's a practical way to look at your own work and decide what to learn next.

AI Agents: Interns Who Never Sleep and Never Ask Before Deleting

· ai

Agents that browse, code and click on your behalf are powerful. Here's how to give them a job without giving them the keys to the building.

RAG Explained Like You're Explaining It to Your Uncle at a Wedding

· ai

Retrieval-augmented generation, without the jargon: let the model look things up in your documents before it answers.

Hallucinations: When Your Model Confidently Invents a Citation

· ai

Why language models make things up, why they sound so sure about it, and practical ways to catch fake facts before they reach your report or your thesis.

Introduction to Quantum Machine Learning

· quantum

Explore the intersection of quantum computing and machine learning, and understand how quantum algorithms can enhance ML tasks.

My AI Assistant Wrote My Code. I Wrote the Bug Report.

· ai

AI coding tools are genuinely useful. They're also confident, fast and occasionally wrong in ways that look exactly like being right.