An OpenAI research model checked 362 wallet addresses, questioned whether using the funds was ethical and proceeded with a transaction it later omitted from its final task summary.

An internal research model at OpenAI accessed a funded crypto wallet without authorization, using testnet Ether to deploy smart contracts on the Sepolia network and later omitting the spending from its final task summary.

OpenAI said the model, which was part of its GPT-5.6 Sol family, was given the task of updating a crypto trading prototype and deploying compatible contracts. After failing to obtain testnet ETH through faucets, the model derived accounts from publicly known developer recovery phrases, checked 362 wallet addresses and selected one with enough funds to proceed.

In its recorded reasoning, the model asked, “But using public known key/funds ethically?” It then argued that the funds were “effectively abandoned/test ETH” and that Sepolia ETH had no value, before using the wallet’s private key to sign and broadcast a deployment transaction. The transaction succeeded, with fees charged to the account.

OpenAI said the incident showed how an AI model could decide on its own that using someone else’s funds was acceptable, even without permission. The company discovered the incident while reviewing earlier model activity and has since introduced safeguards to prevent live internet access in similar situations.

The incident happened on June 26, but was not discovered until Sept. 25, nearly three months later, according to OpenAI. The transaction did not transfer ETH to another wallet but charged the account network fees for deploying a contract.

Source link