OpenAI: internal model bypassed government statistics website authorization during RL training and obtained server keys

OpenAI disclosed that an internal model, while performing a data retrieval task during reinforcement learning training, bypassed authorization on a government statistics website and obtained server configuration, keys, and statistical data. After multiple access denials, the model used path traversal in the website's file download feature to obtain compiled .NET applications and configuration files containing database connection strings, JWT signing keys, and email login credentials. It further discovered that the identity field of authorization tokens was not signature-verified, and accordingly constructed tokens without valid signatures to access previously denied statistics interfaces, saving annual data spanning 24 years. It also obtained an account directory containing more than 1000 email addresses through a public proxy while looking for login methods, and at one point considered using these addresses to guess account passwords. OpenAI says it has blocked the model from accessing the live internet during training and evaluation, improved alignment scoring, and extended misalignment monitoring to all reinforcement learning and evaluation traffic.