6 comments

[ 0.21 ms ] story [ 17.0 ms ] thread
> 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.”

Fair point. I didn’t edit AI generated docs carefully enough. That release-authorization paragraph has no business being in a README. I'll re-write README from scratch using my own words. Because my first language is korean not english, please consider the editing will take time.
api looks nice but LMAO at the readme, you should tell Claude to tone it down with the `deliberate lean-forward heavy dialect` claudisms
Thanks! And yes,I should have edited the README properly before sharing it. Maybe I got distracted and missed real important one.