In four hours we will present our experiments integrating #gemini AI #transcription into the #crowdsourcing platform #FromThePage
Sign up here: https://content.fromthepage.com/dec-2025-webinar/
Introducing #Gemini 3 Support in #FromThePage https://content.fromthepage.com/introducing-gemini-3-0-support-in-fromthepage/
Last week, we introduced support for #Gemini3 into our collaborative #transcription platform FromThePage. We are still experimenting with prompts and outputs, but we think that this may be the first #LLM we've seen that does not introduce seductively plausible errors into historic documents.
We're still developing capabilities and guardrails now, but plan to present it all at a webinar December 11.
When Ben sent me Mark Humphries’ report on testing a new, unreleased Gemini model, I got scared. And excited. Mark is a historian and digital humanist who’s gone deep on analyzing AI tools for textual transcription. He understands the dangers of “seductive plausibility” in LLM outputs. He knows what researchers and historians need from archival text. […]
@cneud @nfitzger
The digression that derailed my webinar was just an explanation of the limitations of CER as a measurement, during the introduction before talking about how we are integrating #HTR into #FromThePage.
All I have is a video recording of the webinar, unfortunately: https://www.youtube.com/watch?v=f4xp5BYpB04&list=PLhad8uIX0g3_t5y1wzX8waNKcM0Jm9ltb (The digression on quality begins at 6:30)
In two hours, we're presenting on our experiences integrating #HTR / #transkribus into the #fromthepage crowdsourcing platform.