Foundation Models On-Device LLM: The Tool Protocol
iOS 26's Foundation Models framework puts a 3B-parameter LLM on every Apple Intelligence device. The Tool protocol is the surface that makes the model useful.
AI & TechnologyWriting
Thoughts on design, development, AI infrastructure, and building products.
watchOS Runtime Is a Contract, Not a Background Task
watchOS has no iOS-style background. WKExtendedRuntimeSession is the contract; without it, the app suspends on wrist drop. Pattern shipped in Return.
AI & TechnologyHealthKit + SwiftUI on iOS 26: Authorization, Sample Types, and Cross-Platform Patterns
Real production patterns from Water (water tracking, HKQuantitySample) and Return (mindful sessions, HKCategorySample). Permission UX, async wrappers, watchOS variants, and the trap to avoid.
AI & TechnologyLiquid Glass in SwiftUI: Three Patterns From Shipping Return on iOS 26
Apple's Liquid Glass is a one-line SwiftUI API. Three patterns from Return go beyond .glassEffect(): glass on text via Core Text glyph paths, mirror reflection, and HUD overlays.
AI & TechnologyFive Apple Platforms, Three Shared Files: How Return Actually Ships Cross-Platform SwiftUI
Return runs on iPhone, iPad, Mac, Apple Watch, and Apple TV. Three Swift files are shared across all five targets out of 40 total. The rest is duplicated, and that is on purpose.
AI & TechnologyClaude Code Mac Desktop + Remote Control: A CLI User's Guide
What changes when you move from `claude` in a terminal to the Mac desktop app, and how /remote-control lets you steer a local session from your phone without losing Xcode, MCP, or files.
AI EngineeringMCP Server Alongside an iOS App: Two Agent Ecosystems, One List
Get Bananas runs on iOS, macOS, watchOS, and visionOS. It also lives inside Claude Desktop as an MCP server. Bridge: iCloud Drive plus a JSON file.
AI & TechnologyApp Intents Are Apple's New API to Your App
I shipped an App Intent in Water on Feb 8, 2026. Here's what Apple Intelligence wants from third-party apps in iOS 26, and why App Intents are the contract that matters.
AI & TechnologyThe Cleanup Layer Is the Real AI Agent Market
Charlie Labs pivoted from building agents to cleaning up after them. The AI agent market is moving from generation to proof. Cleanup is the durable layer.
AI & TechnologyThe Repo Shouldn't Get to Vote on Its Own Trust
Two Claude Code trust dialog bypass CVEs in 37 days reveal a load-order failure. One invariant fixes it: interpret no workspace byte until the path is trusted.
AI & TechnologyReward the Tool Before the Answer
AI agents fail when answers claim tool work that never happened. Four failure modes and the rule that catches them, with a tool-supervised RL parallel.
AI & TechnologyThe Steve Test: Does the Work Deserve to Exist?
Steve Test vs Jiro Test: a product framework for deciding whether work deserves to exist, holds user trust, and belongs in the whole you are building.
Career & GrowthExternal Publications
Technical writing at Introl
Local LLM Hardware Pricing Guide 2025
Comprehensive hardware recommendations and cost analysis for running large language models locally.
H100 vs. H200 vs. B200: Choosing the Right NVIDIA GPUs for Your AI Workload
GPU selection guide comparing NVIDIA's latest datacenter accelerators for different AI workloads.
TPU Architecture: Complete Guide to Google's 7 Generations
Deep technical dive into Google's Tensor Processing Unit evolution from TPUv1 to TPUv5.
GPU Memory Pooling in Multi-Tenant Kubernetes
Resource sharing strategies for GPU clusters in containerized environments.
Ray Clusters: Distributed AI Computing Infrastructure
Guide to building and managing distributed AI computing with Ray framework.
DeepSeek V3 Open Source AI Cost Advantage
Analysis of open source LLM economics and DeepSeek's competitive positioning.
NVIDIA Vera Rubin GPU 600kW Racks 2027
Future datacenter power requirements and NVIDIA's next-generation GPU roadmap.
SMR Nuclear Power for AI Data Centers
Small modular reactor solutions for powering next-generation AI infrastructure.
DeepSeek MHC Architecture Breakthrough
Technical analysis of DeepSeek's Multi-Head Compression architecture innovations.