8 points | by Clickin 5 hours ago ago
4 comments
> 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.”
api looks nice but LMAO at the readme, you should tell Claude to tone it down with the `deliberate lean-forward heavy dialect` claudisms
[dead]
> 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.”
api looks nice but LMAO at the readme, you should tell Claude to tone it down with the `deliberate lean-forward heavy dialect` claudisms
[dead]