They were almost certainly not doing the OCR on the device. Such a CPU would be too power-hungry and the process would still be too error-prone given the limited compute. They would just send the raw data to the C2, which could send it to an emulator, snapshot the output and send it to an LLM.
They were almost certainly not doing the OCR on the device. Such a CPU would be too power-hungry and the process would still be too error-prone given the limited compute. They would just send the raw data to the C2, which could send it to an emulator, snapshot the output and send it to an LLM.