Generative AI
Revisiting Gorillas in Godot 4: Gemini 3.1 Pro Takes the Challenge
Benchmarking Gemini 3.1 Pro against the 1991 QBasic Gorillas challenge yields a bug-free build on the first attempt, but Claude Opus remains the undisputed champion.
Gemini achieves working gameplay only by …TL;DR
TL;DR — Quick Summary & Key Takeaways
Pushing the Limits: Running Gemma 4 Locally on Apple Silicon
Running local LLMs with Ollama offers complete data privacy and zero API subscription costs on consumer hardware.
Pairing Ollama with efficient small models like Gemma enables fast, offline generation for everyday …TL;DR
TL;DR — Quick Summary & Key Takeaways
Why Google AI Pro is the Best Value AI Subscription in 2026
Google AI Pro offers exceptional value for software engineers and power users by bundling massive context windows with Gemini Advanced and ecosystem integration.
Its combination of generous token limits, Workspace …TL;DR
TL;DR — Quick Summary & Key Takeaways
Vector Databases: What They Are and How To Use Them
When text embedding collections expand beyond simple in-memory arrays, brute-force linear search introduces severe latency bottlenecks.
Vector databases solve this challenge using approximate nearest neighbour …TL;DR
TL;DR — Quick Summary & Key Takeaways
Claude Code vs Codex: Recreating an Iconic Game
Challenging Claude Code (Opus 4.6) and OpenAI’s Codex (GPT-5.3) to recreate the 1991 QBasic game Gorillas in Godot 4 reveals starkly different coding philosophies.
Claude delivered a delightful, authentic …TL;DR
TL;DR — Quick Summary & Key Takeaways
How To Use Text Embeddings
Text embeddings convert unstructured prose into dense mathematical vectors that capture contextual semantics rather than exact keyword matches.
Generating and comparing embeddings locally with open Python …TL;DR
TL;DR — Quick Summary & Key Takeaways
Using Agentic AI to Get the Most from LLMs
Agentic AI represents a generational leap forward in how artificial intelligence systems operate, moving beyond single, monolithic models to autonomous, goal-oriented agents.
If you missed it, my previous article on how LLMs work under the hood lays the foundation for how large language models …
Unlocking the Power of Local Offline Language Models: Set Up Ollama for Free
In today’s landscape of privacy, speed, and cost-conscious development, running large language models (LLMs) locally is becoming essential for both enthusiasts and professionals. Whether you’re working on Mac, Windows, or Linux, this straightforward guide will show you how to set up Ollama—an …
Everything you need to know about how LLMs like ChatGPT work
Large Language Models (LLMs) are the most talked about technology of the past 2 or so years, particularly OpenAI’s ChatGPT which seems to get a new version come out every few months. But can you say you know how this technology works or where its limitations lie? Today we take a deep-dive on …
How to use GitHub Copilot Free in Visual Studio Code
Microsoft announced on 18th December 2024 that they were introducing a free tier for GitHub Copilot. So what does this mean, how do you set it up and how can you use it? This post focusses specifically on the integration with Visual Studio Code, but you can use GitHub Copilot with any supported IDE. …