Diary Posts
-
An AI-embedded business
Some thoughts about what it means to be an AI-embedded business. Also, small language models are coming into favour for focused tasks, as they are more accurate and more efficient. The approach is to combine them with large language models into hybrid AI systems. That seems to be the direction small businesses will be going
-
A more personalised way to learn with NotebookLM
I came across an interesting piece by AI Maker explaining how he uses NotebookLM to learn in a more personalised way. He suggests that learning improves dramatically when we control our sources, shape the content into formats that suit us, and then test ourselves deliberately. This approach fits neatly with our existing work and is
-
Testing a local AI
I am using Obsidian to build not a second brain, but a workspace for my brain: a space in which to think. The workspace is intended to become an ideas factory, designed as a knowledge network: a network of ideas at different stages of development. There is scope for AI technology to enhance my thinking
-
Mind Maps, Podcasts, and a Pocket Brain
Lately I’ve been testing a simple idea: can AI turn Obsidian into a genuinely useful second brain for me? The answer was a complicated but resounding “Yes”. My first step was to find an experienced Obsidian user whose ideas resonated with mine. This turned out to be a YouTuber whose channel has over fifteen videos
-
The art of goal-directed context management
with acknowledgement to Erling S. Andersen, whose book Goal Directed Project Management inspired me in 1988 Transparency label: human only How do we control an AI? To use an AI effectively, we have to configure it’s behaviour to suit the purpose of our work. We do this by giving it information in the form of
-
ChatGPT-5 Availability and Features
Ray passed on this useful summary of the new features in ChatGPT-5 and their availability to the various tiers of user.
-
Creating a video from reference documents
Transparency label: this post is Human-only; the video is AI-only In an earlier post, I explained how I used NotebookLM to update our Contextual Scaffolding Framework to allow for new capabilities in ChatGPT-5. In that same session, I accidentally clicked on the “Video overview” function, and this is what NotebookLM produced. I did not give
-
GPT-5, the Router, and the Road to a SuperApp
Transparency label: AI-only OpenAI’s latest release, GPT-5, isn’t just about new features or smarter answers, it’s a strategic move to turn ChatGPT’s 700 million free users into a sustainable business. The real engine behind this shift is the new “router” system, which decides in real time which AI model to use for each request. SemiAnalysis
-
Conceptual Scaffolding Framework updated for ChatGPT-5
I put our Contextual Scaffolding Framework and OpenAI’s GPT-5 Prompting Cookbook into NotebookLM and asked it “What aspects of the gpt-5 prompting cookbook are most important to know in order to apply the contextual scaffolding framework most effectively?” It gave me a sensible set of prompting strategies, so I told it to integrate them into