miniblog.

Assertions are a surprisingly nuanced design space. In a test, if I assert `x < y`, I really want to see the values of x and y when it fails. Do you define an API for every possible predicate (Python's assertLess, expect.js) or try to support the native syntax (c.f. pytest)?

The word "agent" is so overloaded in the AI space. Sometimes it means a sophisticated interaction system, but other times it just means API. I think it's partly a sign of how new the space is. We don't have consensus on the best way to use these systems yet.

I'm surprised by how many different weather forecasts I can get out different apps. Surely there aren't many API providers for weather predictions? Alternative conspiracy theory: do weather apps that predict nicer weather get more downloads?