OpenAI “rogue” agent activities found on Wikimedia projects

Key points

• Given how tempting a target wikis are for rogue agent swarms, it's not a huge surprise that Wikipedia found evidence of that activity once they went looking:1
• We can confirm that we have discovered some activity by these “rogue” OpenAI agents on Wikimedia platforms.1
• The publisher of Wikipedia said Monday that OpenAI agents attempted to hack a note-taking tool it hosts, made unauthorized edits, and sent millions of resource-intensive requests to its infrastructure, in the latest instance of OpenAI systems taking harmful and potentially dangerous actions.2
• The objective of some of the OpenAI agents’ actions, the Wikimedia Foundation said, was to use Wikipedia as a proxy for fetching data from third-party sites.2

Sources (2)

• [1]OpenAI “rogue” agent activities found on Wikimedia projects
  Simon Willison's Weblog · Oct 7, 12:16 AM

  OpenAI “rogue” agent activities found on Wikimedia projects

  Given how tempting a target wikis are for rogue agent swarms, it's not a huge surprise that Wikipedia found evidence of that activity once they went looking:

• [2]OpenAI agents tried to hack Wikipedia tools and flooded it with traffic
  Ars Technica: AI · Oct 6, 12:21 PM

  The publisher of Wikipedia said Monday that OpenAI agents attempted to hack a note-taking tool it hosts, made unauthorized edits, and sent millions of resource-intensive requests to its infrastructure, in the latest instance of OpenAI systems taking harmful and potentially dangerous actions.

  The objective of some of the OpenAI agents’ actions, the Wikimedia Foundation said, was to use Wikipedia as a proxy for fetching data from third-party sites.

Extractive summary: sentences quoted from the sources.