// pub
Knowledge Representation and Reasoning
-
Structure All the Way Down: Finding (and Building on Top of) the Tectonics Underneath Any Domain
Generative AI functions like a stochastic parrot and feels like herding cats. Our way, we hope, makes it more of a reasoning bedrock that captures categorical reasoning.
-
The Emergent Structure of Natural Language: Our Spin on Knowledge Representation & Reasoning Heuristics
A KRR is a set of ontological commitments — a representation that carries a theory of reasoning. So it doesn’t just store what’s known, it sanctions and recommends inferences atop what’s known. When that representation is natural language, those commitments and that reasoning theory are already in the words.
-
How Structure and Language Choices Impact Prompt Engineering for LLMs
Choose a prompt: Your output should embody brevity. Or: Your output should demonstrate brevity. This isn’t a trick question. It’s a practical problem in the age of ChatGPT, Gemini, Claude — or whatever flavor of generative AI (genAI) large language model (LLM) you prefer. Because interestingly (and frustratingly), when you interact with genAI LLMs, the…
-
ChatGPT Vs Gemini Vs Prompting: Experimenting with GenAI Output Quality & CORE Heuristics
Comparing ChatGPT and Gemini output and developing online content heuristics