Corey_

What’s more worrying isn’t that they tested—it’s that the existence of the test feels like a smoking gun. That says more about our broken trust in institutions than anything else.

Humans may not update like Bayesians, but we read context, shift priorities, and act under pressure. Judgment isn't just math — it's lived experience, intuition, and meaning in motion. That’s still hard to replicate.

I completely agree that TypeScript is ideal for LLMs. The type system and the extensive training data make it the best choice. But as someone who's been working with TypeScript for a while, I still see LLMs struggling with complex generics or even simple types. It’s better than before, but still far from perfect.

Also, TypeScript error messages can be a pain. When LLMs encounter something like "SomeType is not assignable," instead of handling it properly, they often just cast it to any. This happens way too often.