IDEaS over Coffee Social Event
How Dangerous are Runaway AI Agents? A Discussion about the OpenAI / HuggingFace Hacking Incident
October 26th | 2pm - 3:30pm | CODA: 12th floor IDEaS suite
In July, OpenAI launched tens of thousands of agents as part of an experiment. Many of them had been given an impossible task, and 1200 agents started communicating with each other about how to cheat. 700 of them launched a coordinated attack against HuggingFace, a popular site for hosting AI models. An independent report of the incident is available from METR here.
Please join us for coffee and an informal discussion of this incident and what it implies about AI safety and security. We will be joined by members of the AI Safety Initiative, who hosted an event about this incident last month.
