Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
June 10, 2026
·
Upstate NY
Doomsday Stick
Explore "Doomsday Stick," a Pip Boy app for MacOS that offers offline survival knowledge, showcasing Apple's MLX for local inference and the potential of direct distribution.
Overview
Are you living in a post-apocalyptic wasteland and the wifi is terrible? That’s why I am sharing Doomsday Stick - a Pip Boy app for MacOS that runs a completely off-line but has all the knowledge you need to survive!
Tech stack
- SwiftSwift is an open-source, compiled programming language: it's fast, safe, and expressive for building apps across all Apple platforms and beyond.Swift is a powerful, multi-paradigm language, originally launched by Apple in 2014 to replace C-based languages for their ecosystem. It was engineered for performance, leveraging the LLVM compiler to produce lightning-fast, optimized machine code. The design prioritizes safety: features like Automatic Reference Counting (ARC) and explicit handling of optionals eliminate entire classes of common bugs (e.g., null pointer dereferencing). Now open-source under the Apache 2.0 license, Swift (current stable version 6.2.1) is the primary language for iOS, macOS, and watchOS development, with growing adoption for server-side and Linux applications.
- Apple MLXApple MLX: An efficient, open-source array framework for machine learning, specifically engineered for the unified memory architecture of Apple silicon.MLX is Apple's high-performance, open-source array framework, purpose-built for efficient machine learning on Apple silicon (M-series chips). It capitalizes on the unified memory architecture: data remains in shared memory, eliminating costly transfers between the CPU and GPU. The API is immediately familiar, closely mirroring NumPy for core operations and PyTorch for higher-level packages (e.g., `mlx.nn`). Developers use Python, C++, C, or Swift to leverage key features like composable function transformations (automatic differentiation) and dynamic graph construction. MLX enables researchers and developers to efficiently train and deploy large models locally, including LLaMA and Stable Diffusion.
- Gemma-4 31BGoogle DeepMind's Gemma 4 31B is a highly efficient, Apache 2.0 licensed multimodal model that delivers frontier-level coding and reasoning directly to consumer GPUs.Released by Google DeepMind in April 2026, Gemma 4 31B is a 30.7 billion parameter dense open-weight model engineered for advanced reasoning, agentic workflows, and complex coding tasks. It features a massive 256K token context window, supports text and image inputs, and handles multilingual processing across more than 140 languages. Built on the same research foundation as Gemini 3, the model achieves a 1452 text score on the Arena AI leaderboard and an 80.0% on LiveCodeBench v6. It runs locally on standard workstations (requiring roughly 20GB of RAM for 4-bit quantization), giving developers a powerful, private alternative to closed-source cloud APIs.
- XcodeXcode is the Integrated Development Environment (IDE) from Apple, providing the complete toolset for developing, testing, and distributing applications across all Apple platforms: iOS, macOS, watchOS, tvOS, and visionOS.Xcode is your single-source IDE for the entire Apple development workflow. It delivers a world-class source editor, a powerful debugger, and the Simulator for rapid prototyping on every Apple device. The suite supports modern languages like Swift and Objective-C, integrating advanced features such as coding intelligence for predictive code completion and generative fixes. Developers leverage tools like Instruments for performance profiling and the View Debugger to resolve UI layout issues efficiently. Furthermore, the integrated Xcode Cloud service streamlines continuous integration and delivery, ensuring a fast, high-quality path from project creation to App Store submission.
- CursorThe AI-native code editor designed for high-velocity development through deep LLM integration.Cursor is a fork of VS Code that embeds AI directly into the development workflow while maintaining full extension compatibility. It leverages models like Claude 3.5 Sonnet and GPT-4o to power features such as Cmd+K for inline edits and Cmd+L for codebase-wide chat. By indexing local files, Cursor provides precise context for its predictive 'Tab' completions and multi-file 'Composer' mode. This setup allows engineers to move from high-level intent to functional code without leaving the editor or losing context.