https://www.gravatar.com/avatar/a7cc4843f7c957afe8575b1f8c45ef44?s=240&d=mp

Multifarious musings from my meandering mind...

To see posts in Esperanto or Shavian (𐑖𐑱𐑝𐑾𐑯), use the language selector at the top of the screen.

My AI Teaching Setup, Part 0: A Life in Plain Text

This is the first of a few articles about the AI system I use for teaching maths. Basically, ten months ago I decided to buy an AI subscription to learn more about the technology, and today I run a small fleet of machines and agents that draft my lessons, check my exams, index my syllabus, and argue with me about design at midnight. This first article is about the recent years before any of that, because it turns out to be the part that made everything else possible.

AI Agents and Local LLMs

In my last article on AI agents I talked about using Claude Code AI agent. This is an easy-to-set-up commercial solution that gives excellent results. The risk is that the pricing may not remain as affordable as it is today, and as a result I wanted to find an alternative solution that insulates me from changing commercials.

There are a number of open-weight models that one may download and run locally on your home computer. Some of the benefits are:

AI Agents Take Over Lesson Prep

It has been a while since I have written about how I use Emacs/LaTeX to generate lesson notes for my students. Quite a lot has happened during that time. One of the main game changers has been the advancements in “AI” technology. Over the next few articles I intend to describe my journey as I navigate this technology and apply it to my teaching practice.

Chat Bots

Having decided to dip my toe in the water, I signed up to two of the prevalent players in this space, being Google Gemini and Anthropic Claude. My early experiments with ChatGPT had led to some disappointing results, where it emphatically tried to convince me that the value of Euler’s constant is 1.5. Since then, the technology has advanced significantly, and I thought it worthwhile to try again.

Plain Text Accounting with Emacs – Part 3

My journey into using Hledger with Emacs to track my share investments continues. Last Time I looked at a way to track shares using a plain text file. Since then I have made some tweaks to my workflow as I gain more experience:

  • naming conventions that support multiple stock brokers
  • booking brokerage fees in a better way to support the Australian tax system.

Naming convention

Over the past month I was not overly impressed with my existing stock broker, which led me to explore other stock brokers that may offer a more reliable service at a cheaper rate. It is expensive to transfer stocks over to a new broker, so I decided to cap further investment at my current broker and instead make any new purchases at a different broker. This meant that I would need an account structure that lets me easily identify which share lots were purchased through which broker.

Plain Text Accounting with Emacs – Part 2

Following up from my previous article on using Emacs to maintain a plain-text ledger for use with plain text accounting software: I reconfigured my Doom Emacs to use the pre-packaged Ledger mode, and I can confirm that it is much nicer to use than the hledger mode I was using before. This could be because I hadn’t set up the hledger-mode configuration properly, but with ledger-mode I find the autocompletion works much better, and the M-q keystroke can be used to nicely line up the amounts in a transaction.

Plain Text Accounting with Emacs

For a while I have been concerned that I haven’t really been on top of my finances as well as I should be, and I decided to bite the bullet and do something about it. I’ve been looking to get much better visibility into my share portfolio, and make sure I track it properly so that if I sell any shares I can easily calculate captital gains and such at tax time. I am also keen to get a better idea of my spending patterns so that I can see where I may be wasting money.