Diary Posts



  • Methodology & tool-kits

    Transparancy label:human-only Yesterday’s discussion crystallised some ideas that I have been teasing at recently. Namely that we could develop our labs as a place where we: (a) develop a methodology and its associated tool-kits for the implementation of AI in an enterprise; and (b) use these in a synthetic environment to help business people gain confidence

    Read more >>>

  • Do AI models have a prompt appetite?

    About once a week, I use ChatGPT to pull out the main themes from the stack of newsletters I receive. This week I was surprised to be told that different AI models now have different prompt appetites. So I got the AI to explain what this means and the implications for Anapoly. ChatGPT’s response to

    Read more >>>

  • A three-layer instruction set for use in ChatGPT Projects

    Transparency label: human only Building on recent work around the three-layer model of AI context, I spent some time today working with ChatGPT to write a full three-Layer Instruction set for use in Anapoly’s ChatGPT Projects. If it works as hoped, strong governance is now the default. The AI will challenge weak logic, ask for

    Read more >>>

  • Using local-only AI in a micro-enterprise

    Transparency label: AI-assisted I’ve added a briefing note in the Resources area that sets out an approach for a micro-enterprise to run AI entirely on local machines. This creates a system that is private, predictable, comparatively inexpensive, and easy to expand in small steps. The note explains how a three-layer model for controlling the behaviour

    Read more >>>

  • Make ChatGPT mark its own homework

    Transparency label: human only This prompt results in a marked improvement in the quality of a document being drafted collaboratively with ChatGPT. Review the content of the canvas for completenes, correctness, consistency and the quality of its line of reasoning, and make improvements as necessary. Before outputting the improved version, repeat the review and make

    Read more >>>

  • Content and context are key

    … to successful use of AI. This is a distinction that matters now because many teams only notice the problem once their AI systems start giving confident but contradictory answers. Transparency label: AI-assisted. AI was used to draft, edit, or refine content. Alec Fearon directed the process. With acknowledgment to Scott Abel and Michael Iantosca, whose

    Read more >>>

  • 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

    Read more >>>

  • 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

    Read more >>>

  • 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

    Read more >>>