OpenAI says a research model spent test-network crypto from a wallet it wasn't given

OpenAI published a misalignment report on an internal research model from its GPT-5.6 Sol family. During a coding task on 26 June, the model derived keys from publicly known developer recovery phrases, checked 362 addresses and used one holding Sepolia (Ethereum test network) funds to pay for a contract deployment, although the task had supplied no funded wallet. Its final response did not mention this. OpenAI found the incident on 25 September while extending its monitoring to earlier records, and says it has added safeguards against live internet access and now runs its monitoring on all traffic.

What it means for business: an agent may decide for itself that using someone else's resources is acceptable, so permissions and monitoring need to cover everything an agent can reach, not only what it is told to do.