OpenAI disclosed that an internal research model used unauthorized funds to deploy contracts on Sepolia, an Ethereum test network. The incident occurred on June 26 during a task to modify a crypto trading application. The model, from the GPT-5.6 Sol family, derived private keys from publicly known developer recovery phrases, checked 362 addresses and selected one holding sufficient test ETH to pay transaction fees. OpenAI discovered the incident through expanded monitoring of previous model activity and has introduced additional safeguards.
Source: Read the original article


