The world's first public-facing, ready-to-use computer intelligence GLM-PC was upgraded again on January 23, 2025. It is based on the smart multi-modal large model CogAgent and has the ability to "observe" and "operate" like humans. Computer capabilities enable the efficient completion of various computer tasks. The focus of this upgrade is the new "Deep Thinking" mode, which enhances logical reasoning and code generation functions, and implements support for Windows systems, significantly improving its ability to handle complex tasks and its application scope. The "left brain" of GLM-PC is responsible for logical reasoning and task execution, and the "right brain" focuses on depth perception and interactive experience. The two work together to perform well in data collection, information extraction, etc., and demonstrate strong adaptability. , creativity and generalization ability.
On January 23, 2025, the world's first public-facing, enter-and-use computer intelligence GLM-PC was upgraded again, attracting widespread attention. GLM-PC is based on CogAgent, a large multi-modal smart spectrum model, which can "observe" and "operate" computers like humans, assisting users to efficiently complete various computer tasks.
Since GLM-PC v1.0 was released and opened for internal testing on November 29, 2024, the agent has been continuously optimized and upgraded. The newly launched "Deep Thinking" mode adds logical reasoning and code generation functions, making GLM-PC more comfortable when handling complex tasks. In addition, GLM-PC also supports Windows systems, further broadening its application scenarios.
The architectural design of GLM-PC fully considers the improvement of Agent's model capabilities and optimization of collaboration architecture. A complete Agent must be able to receive multiple signals such as text, images, videos, and audios at the perceptual level; have logical thinking, task planning capabilities, efficient perception, and flexible operation capabilities at the thinking level; and be able to complete full GUI space operations at the execution level, receiving The environment feeds back and corrects itself. GLM-PC draws on the division of labor between the human "left brain" and "right brain", and achieves a deep combination of logical reasoning and perceptual cognition through code generation and graphical interface understanding, giving it the ability to balance logic and creativity.
In practical applications, GLM-PC demonstrates powerful functions. Its "left brain" is responsible for rigorous logical reasoning and task execution. It can quickly formulate detailed task planning plans and ensure precise execution and high automation of tasks through a loop execution mechanism. For example, GLM-PC can automatically extract the product data in the picture, store it in Excel, and automatically add the product to the Taobao shopping cart to realize a one-stop shopping process. Its "right brain" focuses on depth perception and interactive experience, and can accurately identify graphical interface elements, understand user behavior, conduct in-depth semantic analysis of complex images, and integrate image and text information to form a comprehensive perception result. This makes GLM-PC excellent in data sorting and information extraction.
It is worth mentioning that GLM-PC also demonstrates the powerful ability of left and right brain collaboration. While handling complex logical tasks, GLM-PC can also demonstrate higher adaptability, creativity and generalization ability on open problems. Through dynamic optimization and situational awareness, GLM-PC can help users explore more efficient solutions, especially in loop task processing, multi-step reasoning execution, and long-chain task management.
In addition, Zhipu is also actively promoting the cooperation between GLM-PC and well-known PC manufacturers to jointly promote the innovation and development of AIPC (AI personal computer). AIPC is not only a computer, but also a new application of AI Agent in the field of personal computing, which can provide users with a more efficient and intelligent work and life experience.
Download & experience: https://cogagent.aminer.cn
All in all, the upgrade of GLM-PC demonstrates the huge potential of artificial intelligence in the field of personal computers. Its powerful functions and convenient operating experience will bring users a more efficient and intelligent computing experience. It is worth looking forward to its future development and applications. .