Home

Latest updates

• (26.1017): On page 00 Why Foundry? a new section Comparing PC and Foundry to understand ontology
• (26.1011): On page 3c Enterprise a new section 0 Core Foundry Enterprise Concepts
• (26.1010): Heroes. A new top level webpage.
• (26.0914-1002): (while in Wuxi) LOOK MOM! NO WIRES!), (26.0927): 3c Enterprise, (26.0927): Core Foundry Enterprise AI Concepts, _(26.0914): 2.2b ZAI versions of the core ~8 Foundry getting started demos.

---

ZiptieAI demos/documents AI (primarily LLMs), from “tiny” neural networks to enterprise AI (Palantir). ZiptieAI focuses on providing insightful and practical guidance with minimal text and diagrams.

• Readme first
  • Heroes is a short history of the AI industry champions that made the current AI tools possible (and became our heroes).
  • Hacks explains the core of what makes AI tick. The champions/heroes never talk about this aspect of AI, but its critical to understand if you want to make the right AI project decisions.
    
    AI champions have made the AI revolution possible; but when they claim AI is (or soon will be) intelligent, then they are championing a fairly tale that is not in your best interest (the humorous diagram below compares Tweedle Dee and Tweedle Dum from “Alice in Wonderland” with the (internal) agent and transformer (TF) of an LLM)
    
    
    
• AI fast track
  • QS covers selected demos.
  • Concepts summarizes the core concepts (mainly from the QS demos).
    
    AI = deterministic computational algorithms that are extremely useful for specific types of applications.
    
    
    
• AI deep dive
  • 2 NNs demos NNs, CNNs, and transformers (TFs) (the source of the “I” in AI). In this section you control the AI mathematics.
  • 2b Models demos how to build packaged AI models (primarily LLMs). Covers fine-tuning, local models, deployment, and model serving (I am convinced that local models, like local computers 40 years ago, will become the norm). In this section you control the model.
  • 3 Agents. Python agents that implement reliable workflows, using AI models as helpful assistants. You control the application.
  • 3b Workflow platform (such as n8n) demos of practical agentic AI applications. The workflow platform controls the architecture.
  • 3c Enterprise AI demos (current focus is on Palantir). The enterprise platform controls almost everything.
    
    From core NNs to enterprise AI.