An agent scored genealogy matches and missed the matches a human spots at once
A coding agent built and tested complex genealogy record-matching scoring rules against real datasets; results sort of acceptable but it missed human-obvious cases and produced false positives.
This only partly worked. Read what happened before you try it.
How it works
- A coding agent builds and tests complex scoring rules for genealogy record matching against real datasets
- Results are sort of acceptable
- It misses the cases a human finds obvious
Why it’s worth knowing
Obvious to a person is a technical term in matching, and the agent lacked it.
Where it’s from
Summarized from a public post on news.ycombinator.com. See the original ↗