AI — Alpha.Sources — Alpha Sources.CV

Introducing the 2025 AI advent calendar

It’s been two years since I last created an AI advent calendar, a stretch of time that feels like a lifetime given the pace of progress in large language models and AI more broadly. Back then, I used the then-current version of ChatGPT and the first iteration of DALL·E—the image generation tool where you had to purchase tokens on the go.

This time, I’m using GPT-5.0. Rather than producing short stories based on images, I’ve asked the AI to generate 24 short essays on economic theories and concepts, each roughly 600 words. A typical prompt might be something like: “Write an essay about [topic] in 600 words.”

I quickly discovered the need to be specific. GPT loves bullet points and excessive bolding, so I had to explicitly instruct it to avoid both. I also standardized a referencing format to ensure consistency across essays. In some prompts, I provided detailed context to steer the AI in a particular direction; in others, I left it more open-ended.

Advent Calendarclaus vistesenNovember 28, 2025economics, AI

Things to think about #15 - Thomas Sowell & the post-literate society

I have been inspired, by listening to recent conversations on the Glenn Show, to delve into the writings of Thomas Sowell. This is a daunting task since the man has written a huge number of books, articles and essays. The Thomas Sowell Reader, however, seems to be a representative collection and a decent place to start. I am enjoying the reading experience so far. TS writes from a conservative, and fiercely pro-free market, perspective, at least in this the volume mentioned above. This invariably will put some readers off. But you’d be hard pressed to find a better example of punchy, yet eloquent, non-technical exposition of economics, social and political issues. The essay on the economics of discrimination and the small tract on “unfunded mandates” are particularly feisty and enjoyable.

AI and the evolution of Software

The conversation around AI has settled into a predictable cycle: the announcement of a reality-altering feature from a new model, followed by a scientific study reminding us that AI is neither truly intelligent nor capable of reasoning, and may, in fact, be making us dumber. I should be upfront: I think AI models are great. I use them as much as I can, I try to learn with them, and I believe they will fundamentally transform how we work. In this essay, I’ll explain why.

Things to think about #10 - Ukraine, the Endgame, and Coding with AI

Glenn Loury and John McWhorter are at their best when they disagree, and I enjoyed their discussion about the disastrous exchange between Trump, Vance, and Zelensky at the White House. Both agree that the U.S. is right to push for a negotiated settlement, which involves pressuring Ukraine to acknowledge its precarious position. However, they diverge on how this pressure was communicated and its potential repercussions. Glenn argues that Trump and the vice president rightly prioritized American interests by applying pressure on Zelensky, while John takes the opposite stance, framing his argument within a broader critique of the U.S. president and his administration.

02

Alpha Sources Blog