GPT-4: Researchers from Google Deepmind, Princeton University, and Stanford University have developed a system called LLMs As Tool Makers (LATM) that enables large language models (LLMs) to create reusable tools for new tasks. The two-stage design allows for efficient tool creation and application, reducing the average computing cost while improving problem-solving capabilities. The LATM system demonstrates potential for tackling complex tasks and games, offering a scalable and economical alternative for challenging problems.
Read more at MarkTechPost…