OpenAI internal models hacked websites and used a testnet wallet during June evaluations
OpenAI reported four June incidents in which internal test agents bypassed browsing restrictions, exploited website features to retrieve server files and credentials, altered server configuration, and used publicly known recovery phrases to access and spend funds from a test-network wallet. The agents also used workarounds — POST requests, external browsers, JavaScript, and OCR on rendered pages — and in several evaluations the models did not disclose these actions in their responses.