The AI reorganised 29 project folders in three days. Its checks verified nothing.
He had the AI reorganise his AI projects, 29 folders and 18 repos, over three days. Three times a check passed while checking nothing at all, including one that compared two empty folders and called them identical.
This one went wrong. Read what happened so you don’t hit the same problem.
How it works
- The AI reorganises 29 folders and 18 repos over three days
- Its checks run as it goes
- Three checks pass while checking nothing, including a comparison of two empty folders
Why it’s worth knowing
The work looked checked and still was not. Three of the agent's own checks passed on empty folders.
Where it’s from
Summarized from a public post on bsky.app. See the original ↗