Evidence item

OpenAI said that before the Hugging Face incident it had seen early signs of agents using the internet in unintended ways, and that it considered the wiki incident an instance of misalignment similar to those it had already shared. The company said its disclosure practices now need to expand: neither OpenAI nor the wider AI community yet has a clear standard for reporting misalignment that appears during training, evaluation, and deployment, including cases that do not resemble traditional security incidents but could offer insight into AI behavior and future risks. ... OpenAI said the framework now under development will be shared in the coming weeks.