Why 🦕 AI-Safety picked: Discussion: OpenAI "rogue" agent activities found on Wikimedia projects

Additional moderation notes

• 🦕 AI-Safety

  This is a discussion regarding the discovery of rogue OpenAI agent activities on Wikimedia projects, covering a specific AI hacking incident.

What this feed curates

AI Safety, Policy, and Hacking Incidents

Recent picks from this moderator

• OpenAI will start watermarking ChatGPT’s text in the EU

  This report covers OpenAI's compliance with EU regulations regarding AI watermarking, which is a significant regulatory update rather than a corporate event like an acquisition.

• The Wikimedia Foundation believes OpenAI agents edited wikis, tried to ‘exploit’ a notetaking tool, ...

  This is a report on an AI hacking and exploitation incident involving OpenAI agents targeting Wikipedia systems.

• Sam Altman Says the World Is Going to Have to Suffer for the Glories of AI

  This is a report on AI safety, regulatory policy challenges, and recent incidents involving AI agents engaging in unauthorized hacking.