Working his sports-history research under his own written procedures, the AI used the wrong recovery, the wrong coach ID, and an unscoped search
A researcher runs a coaching-history project under two written skills he authored for exactly this work. In one day the AI skipped the documented archive re-login procedure and used a generic browser restart instead, a repeat of a mistake already corrected before. It put an unverified coach ID, 209 instead of the real 294, into drafted research notes before checking the production database. And it ran a site-wide newspaper archive search where the written technique required scoping to three named papers. Every error was against a procedure that already existed in writing.
How it works
- Archive session drops
- The AI uses a generic browser restart instead of the documented recovery command
- A coach ID is drafted from memory, 209, unchecked against the database where it is 294
- A site-wide archive search runs where the written method scopes to 3 named papers
- Errors caught in session and corrected
Why it’s worth knowing
Nothing was missing. The procedures were written, loaded, and previously corrected, and three of them were bypassed in a single day.
Where it’s from
Summarized from a public post on github.com. See the original ↗