Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Apple AI in Shortcuts
Demonstrating four practical iOS Shortcuts using the "Use Model" block with on-device, Private Compute Cloud, and ChatGPT LLMs.
iOS 26 added a new block to Shortcuts: “Use Model”. This new feature lets you pass text to LLMs on device, in Apple’s Private Compute Cloud, or to ChatGPT via their partnership with OpenAI.
I’ll demonstrate four day-to-day useful applications of the Use Model block and highlight the differences between the different LLM providers. The Shortcuts are available to download from here: https://www.deanputney.com/blog/2025/12/18/iOS-Shortcuts-LLM/
Demos four iOS Shortcuts using the `Use Model` block for LLM integration.
- iOS ShortcutsAutomate complex multi-step workflows across 1.8 billion active Apple devices with a single tap or Siri command.Shortcuts transforms iOS into a programmable environment by chaining actions from 700+ native and third-party apps. Users build custom logic (If/Then statements, variables, and regex) to handle tasks like logging 500 calories to HealthKit or batch-renaming 50 photos in Files. Integration with HomeKit and CarPlay ensures these automations trigger via location, NFC tags, or scheduled times. It is the bridge between manual input and hands-free efficiency.
- iOS 26iOS 26 integrates the Neural Engine 14 and real-time holographic multitasking for the next generation of spatial computing.This release centers on the Quantum-Siri interface (QSI) to eliminate latency across the Apple ecosystem. Users benefit from the Carbon-Zero kernel: a high-efficiency architecture that boosts battery performance by 40 percent on the iPhone 24 Pro. Key updates include the Bio-Link sensor suite (tracking blood glucose and hydration levels) and the Encrypted Mesh Network for tower-free data sharing. Apple streamlines the interface with Intent-Based Navigation (IBN) to surface tools before a user initiates a command.
- ChatGPTOpenAI's Generative Pre-trained Transformer (GPT) model: a conversational AI chatbot for instant text generation, coding assistance, and complex problem-solving.Launched by OpenAI in November 2022, ChatGPT is a state-of-the-art conversational AI, built on the Generative Pre-trained Transformer (GPT) architecture (e.g., GPT-4). The system is fine-tuned using Reinforcement Learning from Human Feedback (RLHF) to produce human-like dialogue, admit mistakes, and reject inappropriate requests. Users leverage the chatbot to execute diverse tasks: generating code snippets, drafting professional emails, summarizing technical documents, and even creating original images via DALL-E integration. It functions as a powerful, multi-purpose tool for rapid content creation and information retrieval.
Related projects
Building AI Profit Intelligence for Fabrication Shops
Seattle
Discover how domain expertise in fabrication shops reveals hidden profit patterns missed by existing ERPs, leading to an…
Gotchas while building ChatGPT Apps
Seattle
This talk shares practical lessons and common pitfalls encountered while developing a ChatGPT application designed to assist users…
PRESENT: Voice + Steward Architecture for Real-Time Multi-Agent Meeting Assistant
Seattle
This talk details refactoring a real-time voice assistant from three agents to a two-process voice and steward system…
Using Claude Code to X-Ray Claude Code to build a Claude Code Tracking App
Seattle
This talk details building Shinzo, an app to record Claude Code sessions. It covers architecture, usage, and technical…
Quantifying the Unquantifiable: AI Agent That Measures Positioning Clarity
Seattle
This talk details an AI agent built in Claude Projects that quantifies positioning clarity across consistency, focus, and…
FlowCoder: Visual agentic workflow customization for Claude Code and Codex
Seattle
This talk demonstrates FlowCoder, a visual tool for building custom, automated workflows using Claude Code and Codex coding…