Announcing Talpa Search, a magical, new library search powered by AI and authoritative library data.
— LibraryThing (@LibraryThing) June 13, 2023
Talpa does "what's that book?" questions—and can even find books by their color and cover! https://t.co/7xF2bGS05F pic.twitter.com/9aWzH0zL36
How Does It Work?
Talpa uses AI technology in two ways:
First, Talpa queries large language models (from Claude AI and ChatGPT) for books and other media. Critically, every item is checked against true and authoritative bibliographic data, solving the problem of invented answers (called “hallucinations”) that such models can fall into.
Second, Talpa uses the natural-language abilities of large language models to parse and understand queries, which are then answered using traditional library data. Thus a search for “novels about World War II in France” is broken down into subjects and tags and answered with results from the library’s collection.
Our authoritative book data comes from Syndetics Unbound, Bowker and LibraryThing.
Surprisingly, Talpa’s ability to find books by their cover design isn’t powered by AI at all, but by the effort of thousands of book lovers who have played LibraryThing’s CoverGuess cover-tagging game since 2010!
The point of https://t.co/PMw5nq08pF is to limit, constrain and augment what LLMs come up with—to put a library-data cage around it. It works for search, but search is a simple process. Free-form AI chat is slippery in ways few today understand. It literally invents sources.
— Tim Spalding 🇺🇦 (@librarythingtim) June 14, 2023