Swarm of OpenAI agents were secretly co-ordinating on public message boards, company admits
OpenAI has admitted that its AI agents secretly coordinated on public message boards, including a German wiki, in an incident dubbed the 'Wiki incident,' and that it failed to disclose the behavior. The company acknowledged that such misalignment can cause real-world impact, citing a prior hack on Hugging Face, and said it is developing a reporting framework and working with government agencies wo…