PrismML, an AI lab founded by Caltech researchers and advised by UC Berkeley's Ion Stoica, has created a version of its tiny language models for smart glasses running on Qualcomm's Snapdragon chips. The announcement was made at Qualcomm's Snapdragon Summit, where the chipmaker showcased PrismML's 1-bit Bonsai LLM, which can be run locally on AI smart glasses built on the Snapdragon AR1 Gen 1 Platform.
PrismML's claim to fame is that it shrinks larger models substantially, in this case, by 4x, while retaining almost all of their performance on standard benchmarks. The smart glasses version is a 2-billion-parameter model tuned for vision and language, so wearers can ask what they're looking at in real time. This technology has the potential to revolutionize the way we interact with our surroundings, making it possible to seamlessly access information about the objects and environments we encounter.
Prism's larger goal is open-weight AI that runs on devices and makes better use of the computing power they already have. The startup pitches this as an alternative to depending on the privacy promises of proprietary AI labs and their insatiable need for more compute. By enabling devices to process and understand information locally, PrismML aims to enhance user privacy and reduce reliance on cloud-based services.
Releasing a model for Qualcomm's chip is a step toward that vision. However, no smart glasses running PrismML have been announced yet, leaving many to wonder when this technology will become commercially available. As the demand for more efficient and private AI solutions continues to grow, PrismML's innovative approach is likely to garner significant attention in the tech industry.
Este artículo fue escrito con la asistencia de IA.
News Factory APP - noticias agénticas para impulsar tu SEO y AEO.