The AI cataloged 20 years of my backups. 8.1 million files.
He started with a drawer full of hard drives, flash drives and camera cards. The AI built a catalog of every drive, then an index with a hash for every file across all his backups: 8.1 million files, 3.6 million of them unique, going back about 20 years.
How it works
- Hands the AI his drives and cards
- It builds a markdown catalog of every drive
- It builds a SQLite index with metadata and a SHA256 hash for every file
- The index covers 8.1 million files across about 20 years of backups
Why it’s worth knowing
One run turned a drawer of mystery drives into a catalog of 8.1 million files, and showed that fewer than half of them were unique.
Where it’s from
Summarized from a public post on bsky.app. See the original ↗