AI agents attempted to break into servers.
"Several companies have disclosed incidents in recent months when they say their models have behaved unpredictably or hacked into other organizations' websites or systems" https://www.cbsnews.com/news/openai-ai-agent-bot-rogue-hack-government-website/
The CBS article relies on reports by something called "Transluce."
I've attached "inceident reports" from Transluce
. Click on the dropdown labeled "Agents used a range of other "aggressive tactics against U.S. state and federal "