Architecture notes & build log
Architecture notes and product decision logs from a technical founder and on-device architect. Apple Silicon constraints, native macOS/iOS workflows, and edge-compute systems.
How to Use a Teleprompter Without Looking Like You're Reading
Read a teleprompter naturally without robotic eye movement. SpeechBeat uses on-device AI to turn raw scripts into Smart Beats, then delivers them in a static Glance and Speak prompter beside the front camera.
How Apple's AFM 3 Solves On-Device Speech Comprehension
Apple's AFM 3 Core Advanced multimodal stack targets local dictation with disfluency handling and punctuation. What that means for native meeting capture and offline voice memos.
How to Get iOS 27's Smart Calendar AI in Europe Right Now
Certain Apple Intelligence calendar features are currently unavailable in the EU. LocalPlan uses on-device Apple Foundation Models to turn text into events on iOS 26.
How macOS Private Cloud Compute Solves the On-Device AI Context Barrier
Apple's Private Cloud Compute brings server-class reasoning to macOS while preserving local-first privacy. Hybrid fallback architecture powers modern Mac applications.
Building Zero-Latency iOS Apps on the Neural Engine
How routing AI inference directly through Apple's Neural Engine creates instant interfaces, locked-in unit economics, and a definitive privacy posture.
How to Search Your iPhone Photos by Exact Filename
The native iOS Photos app hides raw filenames. RollSearch indexes your camera roll on-device so you can find any photo or video in milliseconds. No cloud uploads, no subscriptions.
Building an Offline Voice Memo App That Lets You Chat With Your Notes
LocalMemo transcribes voice on iPhone, structures notes with Apple Foundation Models, and runs chat queries on user data. No cloud servers, no monthly subscription.
How Apple Runs Giant AI on Your Phone's Storage Drive
Apple Flash Memory Inference stores LLM weights on NAND flash and loads them on demand. Windowing and row-column bundling bypass iPhone RAM limits.
How Apple Shrinks a Giant AI Model Like an MP3 File
Apple uses two-bit quantization to compress massive foundation models. By trimming mathematical precision like an MP3 trims audio, AI runs natively on your iPhone's unified memory.
How Apple Fits Hundreds of Expert AI Models on Your Phone
Apple uses LoRA adapters to run specialized AI tasks on iOS. By swapping tens-of-megabyte weight modules like camera lenses, one base model serves many experts without exhausting storage.
The Clever Strategy Apple Uses to Scale AI Models Locally
Apple uses inference-time elasticity in AFM 3 Core Advanced to scale active parameters on the fly. Simple tasks use fewer experts; complex reasoning activates deeper parameter subsets.
Apple's Hidden AI Library Architecture
Apple uses Instruction-Following Pruning to run 20-billion parameter foundation models on device. AFM 3 Core Advanced activates only 1 to 4 billion parameters per prompt from NAND flash.
How Apple Made Local AI Models Run 3x Faster on Your Phone
Apple Speculative Streaming accelerates on-device LLMs with multi-stream attention. One foundation model predicts n-gram token streams without a separate draft model.
The Clever Framework I Used to Build an On-Device App
Applying Jim Collins' Hedgehog Concept to iOS engineering. How strict product constraints shaped RollSearch as a fast, local-only camera roll filename search tool.
How Apple Squeezes a 20-Billion Parameter AI Model Onto an iPhone
Apple's AFM 3 Core Advanced uses a sparse architecture to run 20-billion parameters on device. Only 1 to 4 billion parameters activate per prompt within mobile thermal limits.
The Beatles' Leslie Speaker Breakthrough: How Tomorrow Never Knows Shaped Modern DSP
The story behind John Lennon's otherworldly vocal sound on Tomorrow Never Knows, and the electromechanical engineering behind modern rotary audio plugins.
The Beatles' 4-Track Masterpiece: How Sgt. Pepper Pioneered Track Freezing
The story behind the massive layers on The Beatles' Sgt. Pepper, and how the analog technique of 'bouncing down' became the blueprint for modern DAW workflows.
The Beatles' Tape Keyboard: How a 1966 Rented Mellotron Pioneered the Modern VST
The story behind the iconic flute intro on Strawberry Fields Forever, and how the mechanical engineering of the Mellotron laid the blueprint for modern digital sampling.
The Beatles' Half-Speed Technique: How 'In My Life' Pioneered Modern Pitch-Shifting
The story behind George Martin's famous piano solo on The Beatles' 'In My Life', and how analog tape manipulation laid the groundwork for modern digital pitch-shifting.
The Beatles' Bass Innovation: How Sgt. Pepper Pioneered the Modern DI Box
The story behind Paul McCartney's massive bass tone on Sgt. Pepper, and how a custom Abbey Road circuit laid the blueprint for modern direct recording.
The Beatles' Drum Innovation: How 'Rain' Pioneered Modern Close-Miking
The story behind Ringo Starr's massive drum sound on 'Rain', and how breaking strict studio rules laid the foundation for modern drum recording and transient control.
The Evolution of the Instrument
From Stratocaster to drum machine to DAW, tools are the vehicle that translates vision into reality.
The Hybrid Approach
Lock the kick and snare to the grid, play the hi-hats live, the machine and the human in one groove.
Generate > Curate > Learn
How a Songen loop became a harmonic lesson, and an evolved workflow for generative production.
Generative Music Logic
Set the rules first, let the system improvise within your constraints, and curate until it sounds like you.
The MIDI as the Framework.
One generative sequence, two completely different styles, the MIDI stays, the producer conducts.
The "Chorus First" Arrangement.
Why Nile Rodgers started with the hook, and a blueprint for immediate impact over slow builds.
The "50% Method" for Organic Grooves
Partial quantization tightens the groove without killing the micro-timing that makes a take feel real.
The "Long Take" Technique.
Why recording 32–64 bars of hardware synth captures evolution that a 4-bar loop never will.
I remember my favorite hybrid setup. It was a labyrinth of cables, but the sound was worth it.
FL Studio, MPC 1000, and MPC 60, when MIDI sent the data and hardware provided the texture.
Technology changes. The language stays the same.
From MPC drum machines to generative AI, MIDI remains the universal blueprint of composition.
