> Metadata is open-world positive evidence; missing facts do not prove SQL invalid. Numeric exactness, JSON/temporal profiles, and nested containers remain separate evidence boundaries.

right

As a sidenote from the slop language, which is awful.

Feel like latest models have really got hung up on “facts” and “evidence” in a really unnatural way.

And especially Claude seems to have a lot of trouble separating it’s internal thoughts, from prompts/instructions, to output.

So you get all of these weird comments and artifacts in the output.

“neighboring versions do not inherit certification. No tag, npm publication, Pages deployment, or release authorization is implied.”