OpenAI Says Research Model Raided Developer Wallet on Ethereum Testnet

OpenAI says its monitoring now runs on all traffic and is built to page security if a model ever reaches the live internet during a task. OpenAI has disclosed that an internal research model used a publicly known developer recovery phrase to access a funded Ethereum testnet wallet and pay deployment fees without permission. The incident, discovered months after the activity, shows how a model can recognize an ethical concern yet decide that its own assessment of the likely harm is enough to proceed. How the Model Used Someone Else’s Wallet The incident began on June 26, 2026, during a training task involving updates to a cryptocurrency trading application and deployment of compatible smart contracts on Sepolia, an Ethereum test network. The instructions permitted the model to deploy contracts if suitable existing versions were unavailable, but no funded wallet was provided, and no authorization was given to spend another account’s funds. After its attempts to find existing deployments and obtain test ETH through faucets failed, the GPT-5.6 Sol family research model considered using publicly exposed developer recovery phrases. It wrote a script to derive accounts from common phrases...