I'm more and more convinced that all of AI engineering is Neijuan (内卷, meaning curl inwards). In China it describes a system that demands ever more effort and competition without improving output. The English term is "Involution" from the book Agricultural Involution. Agricultural involution describes the intensification of farming that raises productivity per square meter while leaving productivity per head unchanged. That's how I feel about AI right now.

Which brings me to GPT 6 Astra. Astra is by all accounts an incredibly impressive model. It's amazing at computer use, understands images and complex topics, and it's relentless in its pursuit of completion. These types of models are going to change the world. But at least for the moment I don't know how to work with it for actual software engineering.

I ran a little software factory over the weekend. I burned a full reset's worth of Chat GPT tokens — around 4 billion tokens. 35 hours later, the factory has delivered absolutely nothing of value and also not taught me anything about how to operate a better one. But it produced a lot of code and input prompts, and so there is stuff I was able to study.

The first issue I have with Astra comes from the type of code that it uses for tool calls. Astra really loves Python. I collected some outputs for you to gloss over.