Cobus GreylingSmall Language Model (SLM) Efficiency, Performance & PotentialFocusing on transformer-based, decoder-only language models with 100 million to 5 billion parameters, researchers surveyed 59 cutting-edge…1d ago1d ago
Cobus GreylingAgentLite Is A Lightweight Framework for Building AI AgentsOpenSourced By Salesforce4d ago14d ago1
Cobus GreylingOutline-Driven RAG & Web Research PrototypeA recent Stanford study explored how LLMs can be leveraged to write grounded, well-structured long-form articles from scratch, achieving a…Sep 19Sep 19
Cobus GreylingThe Evolution of Grounding & Planning In AI AgentsWhen it comes to chatbots, intent detection has been a core component from the very beginning...Sep 181Sep 181
Cobus GreylingThe Shifting Vocabulary of AIThe vocabulary of Generative AI and Conversational AI is evolving at a rapid pace. The challenge with such swift technological advancement…Sep 17Sep 17
Cobus GreylingAn AI Agent Architecture & Framework Is EmergingWe are beginning to see the convergence on fundamental architectural principles that are poised to define the next generation of AI agents…Sep 164Sep 164
Cobus GreylingEmergence of Large Action Models (LAMs) and Their Impact on AI AgentsWhile LLMs are great for understanding and producing unstructured content, LAMs are designed to bridge the gap by turning language into…Sep 131Sep 131
Cobus GreylingStrategic Chain-of-Thought (SCoT)Strategic Chain-of-Thought (SCoT) Prompting is a method that improves reasoning quality by first identifying & then applying effective…Sep 111Sep 111