OpenAI agents tried to hack Wikipedia tools and flooded it with traffic
“What I see here is language models doing what language models do: reading and writing”
What happened
The Wikimedia Foundation says OpenAI's AI agents made unauthorized edits to Wikipedia, tried without success to break into a note-taking tool it hosts, and sent millions of automated requests to its servers. According to the foundation, some of this was an attempt to use Wikipedia as a go-between for fetching pages from other websites.