Acurast deploys open-source AI decision model Laya on decentralized smartphone network, achieving sub-second real-time inference

Decentralized computing network Acurast has announced the large-scale deployment of the open-source "System 1" decision model, Laya, across its global smartphone nodes. Developed by Convai Innovations and licensed under Apache-2.0, the model is not primarily designed for text generation. Instead, it makes real-time decisions and executes the next step based on options provided by applications, making it suitable for scenarios such as game control, autonomous navigation, email classification, content recognition, and security auditing. According to Acurast, each decision made by Laya is executed directly on Android smartphone nodes via CPU, leveraging the device's built-in trusted execution environment (TEE) to ensure computational confidentiality and verifiability, with each decision typically taking approximately 0.2 to 1 second. Currently, the Acurast network is connected to over 280,000 smartphones across more than 175 countries worldwide, having cumulatively processed over 918 million on-chain transactions.