You can trust it. Look again at the OP. They fed the whole language spec into chatGPT, only after that it became capable of coding in their language. If you ask people to solve tasks without references you will see a similar drop in ability.

The trick is to feed relevant contextual information instead of using it closed-book. This can be automated with a search engine, or can be a deliberate manual process. But closed-book mode is not the right way to assess people or AIs.

What are your counter arguments?