Wikipedia Vandalism Prevention Bot Loop

February 24, 2017

Wikipedia bots meant to remove vandalism clash with each other and form feedback loops of repetitve undoing of the other bot's edits. This issue creates a cycle where both bots continue to make corrections, resulting in an endless loop of edits being undone. The repeated interactions between the two bots can have unintended consequences, such as removing important content or introducing new errors. ...and to learn more, go to https://hisi-project-cerebellum.taim.wiki/measurements/harm-prevention/ai-incident-database/wikipedia-vandalism-prevention-bot-loop

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

Alleged deployer
Wikipedia
Alleged developer
Wikipedia
Alleged harmed parties
Wikipedia users, Wikipedia editors, Wikimedia Foundation

AI governance case studies

For forensic AI governance failure analysis (TAIMScore™ case studies), browse Human Signal’s Failure Files™.

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/7

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.