On the topic of ending uncreating and AI agents
Of all the tools we have created for programming and more, the agentic era has one of the best arguments for ending the age of uncreating. But has it?
Read More →Top Stories
Our language in numbers – Word Representations in NLP
Word representations are a fundamental concept in NLP, enabling machines to understand and generate human language. These are the lecture notes for …
On emergent behaviour, visualising the Boids Algorithm
From simple rules, the Boids algorithm simulates beautiful flocking behaviour creating a complex lifelike pattern. In this post, we visualise the …
How does RRT planning work?
I try to visualise and explain how the Rapidly-exploring Random Tree (RRT) algorithm works with an interactive demo for path planning in robotics. …
Fastest Way to Build Technical Debt
A great warm self-affirming hugging start that slowly changes into a frustrating, melting ice-cream in a winter’s day. I tried the top 3 …
I stopped using Notion and other PKM tools to be more productive
I tried all the popular knowledge management and productivity tools and they all failed in the same way. I now use a much simpler approach to manage …
How to setup VS Code Server HTTPS certificates with Tailscale?
This remote setup, secured with Tailscale and custom certificates, allows my Chromebook to function as a lightweight, always up-to-date gateway to a …
Twelve years later and "man" is still more similar to "doctor" than "woman"
Despite advancements over the last decade, language models like Gemini still exhibit ingrained biases. This persistent issue stems from AI’s …
Structuring LLM Responses with JSON Schemas
Learn how to structure responses from LLMs using JSON Schema to integrate them into pipelines reliably and effectively.
Unwitty burden of Model Context Protocol (MCP)
With an increasing number of large language models (LLMs) being released, the Model Context Protocol (MCP) is a new standard that aims to provide a …