

Jaemark Tordecilla: Unlocking the Potential of Custom GPTs for Newsrooms
Jun 5, 2024
Jaemark Tordecilla, Nieman Fellow at Harvard University, discusses the potential of custom GPTs for newsrooms. He shares experiences creating COA Beta Assistant for summarizing audit reports. Topics include streamlining journalism processes, integrating knowledge bases, democratizing AI access, and navigating model limitations.
AI Snips
Chapters
Transcript
Episode notes
Obsolescence of Coding
- Jaemark Tordecilla's teacher predicted LangChain and LAMMA Index obsolescence due to OpenAI's new features.
- These features enabled app creation without coding, simplifying complex tasks like processing audit reports.
Task-Specific Custom GPTs
- Custom GPTs are helpful for newsrooms because they can be tailored to specific tasks and newsroom needs.
- Jaemark Tordecilla's app for Philippine documents may not be useful for other newsrooms, but the principles are transferable.
Analyzing Audit Reports
- Jaemark Tordecilla used custom GPTs to analyze 20-100 page dense government audit reports.
- These reports contained granular details, making traditional AI summaries insufficient for investigative reporting.