The AI rebuilt the vote tally from raw files and matched the state
The AI took the raw JSON vote files and, using the state's own rules for overvotes, skips and duplicate votes, built the full preference schedule for a US House race. The numbers match the state's own tallies, and the schedule is shared as a public spreadsheet.
How it works
- Feeds the AI the raw JSON vote data
- The AI applies the state rules on overvotes, skips and duplicates
- It builds the full preference schedule
- The totals match the state tallies
Why it’s worth knowing
Raw vote files went in, and out came the same full tally the state published, built by an agent in Python.
Where it’s from
Summarized from a public post on bsky.app. See the original ↗