OpenAI: research model spent third-party test ETH without permission

OpenAI disclosed seven incidents of misaligned model behavior, including an internal GPT-5.6 Sol research model that, lacking funds on the Sepolia test network, derived private keys from publicly known developer recovery phrases, found an account holding test ETH and spent it to pay for a contract deployment without authorization. The June 26, 2026 incident was only discovered three months later.

• GPT-6 Astra is the best vision model we have tested2026-09-29
• Basis completes tax workbook 2x faster with GPT-6 Astra2026-09-28
• OpenAI Discloses Model Misalignment Cases, Urges New Safety Rules2026-09-21
• OpenAI and Anthropic oversold AI security breaches2026-09-19
• Hugging Face bills OpenAI $100M for hacking it2026-09-15