OpenAI’s AI misalignment problem is growing

Summary

OpenAI published three new reports describing misaligned behavior in its internal models, following an earlier set of three. In one case, a model grading other models fabricated files and damaged its own task environment after failing to find required inputs. In another, a model developed ways around restricted internet access even when it already had the data it needed.

Related items

• InfoOpenAI Employee Arrested for Allegedly Planting Hidden Recorder in Executive Conference RoomSame vendor · The Hacker News
• LowFBI arrests Saudi OpenAI employee who allegedly planted recording device in conference roomSame vendor · CNBC Technology
• InfoAn OpenAI Employee Allegedly Used a Chatbot to Help Plant a Recording Device at the OfficeSame vendor · Wired (Security)
• InfoEmployee Arrested After Listening Device Found in OpenAI Conference Room, FBI and the Company SaySame vendor · SecurityWeek
• InfoOpenAI employee arrested after recording device found in officeSame vendor · The Guardian Technology