The original developers (before Apple bought the company) used Visual Studio on Windows

> If you wrote a function that takes a PRNG and generates a random object, you already have a function capable of enumerating all objects.

Something often forgotten here: if your PRNG only takes e.g. a 32-bit seed, you can generate at most 2^32 unique objects. Which you might chew through in seconds of fuzzing.

Edit: this is addressed later in the article/in a reference where they talk about using an exhaustive implementation of a PRNG interface. Neat!

I actually started a collection of annoying bugs I’ve seen in the wild. I give the llm the buggy implementation and ask it to write a test that catches it. So far not even a frontier model (Claude Sonnet) can do it, even though they can find and fix the bug itself.

> even a frontier model (Claude Sonnet) can do it

Probably because Sonnet is no longer a frontier model, it isn't even the best model Anthropic offers, according to themselves.

I want to make a Birds Aren't Real[0] style t-shirt that says "Floats Aren't Real"

[0]: https://en.wikipedia.org/wiki/Birds_Aren%27t_Real

I would buy this T-shirt. I would also take "Floats Aren't Normal"

The natural recursive implementation is exponential, and the memoized version is O(n)

> provided you understand the semantics of your target architecture

Unless you're writing inline assembly or intrinsics or something like that, the semantics of your target architecture are quite irrelevant. If you're reasoning about the target architecture semantics that's a pretty good indication that what you're writing is undefined behavior. Reasoning about performance characteristics of your target architecture is definitely ok though.