Chatwise vs Gadeon

Chatwise turns everything you're learning into knowledge that lasts. Most apps help you look things up. Chatwise helps you remember — pairing a proven spaced-repetition engine with an AI tutor that actually knows your material. It's built to make you sharper, not to think for you. No endless feeds, no busywork — just steady, measurable progress. LEARN IT ONCE, KEEP IT FOR GOOD A daily review adapts to your memory, resurfacing each card right before you'd forget it. A few minutes a day beats an all-nighter — the schedule tunes itself to how well you actually recall, and your streak keeps you honest. AN AI TUTOR GROUNDED IN YOUR MATERIAL Ask anything. Chatwise explains concepts, quizzes you, and turns its answers into flashcards and test questions — searching your wiki and courses first, so it stays accurate and on-topic. It's a study partner, not a shortcut. A PERSONAL WIKI YOU ACTUALLY OWN Capture what you learn as linked pages, with images and PDFs alongside. Your tutor can file notes and keep pages tidy — every AI edit is logged and revertible. Pages are plain Markdown files in your iCloud Drive, so you can open, edit, and back them up with any app you like. COMPLETE COURSES, READY TO STUDY Download courses that bundle readable lessons, flashcard decks, and exams into one path. Work through them section by section — pass a short test to unlock the next — while every card you meet joins your daily review. RECALL FIRST, THEN CHECK Active recall beats passive re-reading. Flip a card, grade yourself honestly, and the interval adapts automatically. PROVE IT ACTUALLY STUCK Short, no-stakes tests go beyond multiple choice — typed answers, math, code, even diagrams — and score against your last run, so you see real progress instead of guessing. SEE HOW IT ALL CONNECTS A living knowledge graph maps every concept and its links, colored by what you've mastered — so you always know what to shore up next. PRIVATE BY DESIGN, YOUR CHOICE OF AI Run fully on-device with Apple Intelligence, or download a local model that works entirely offline — your notes never leave your hardware. Want more horsepower? Connect your own AI provider with your own key. FOR STUDENTS AND PROFESSIONALS Med school or the bar exam, a new language, professional certifications, or simply staying sharp at work — Chatwise fits any subject and any goal. DESIGNED FOR APPLE A calm, content-first interface that feels right at home on Mac, iPad, and iPhone. Decks, courses, and your wiki sync across all your devices, so you can pick up wherever you left off. Download Chatwise and start learning in a way that lasts.

Gadeon runs Qwen3.5 and QwenPaw hybrid language models entirely on your device's Apple Neural Engine, using Core ML as its only framework dependency. There's no C, no Python, and no cloud calls: every token is generated locally, keeping your conversations private. Under the hood, these models mix Gated DeltaNet recurrent layers with a smaller number of attention layers. Gadeon compiles that hybrid architecture directly onto the Neural Engine's dataflow accelerator, so both prompt processing (prefill) and token generation (decode) run on-chip instead of falling back to the CPU or GPU. On an Apple Silicon Mac, prefill measures roughly 2 to 2.4 times faster and about 4.4 times more energy-efficient per token than a Metal GPU baseline, while leaving the GPU free for other work. Conversations in Gadeon are append-only: each turn extends the model's fixed-size recurrent state instead of re-processing the entire chat history, so response latency doesn't grow as a conversation gets longer. The app can also roll back to an earlier point in a conversation, dropping reasoning traces or replaying tool calls in a clean form without reprocessing everything from scratch. For ternary-quantized models, Gadeon switches to a pure-Swift Metal GPU backend behind the same session and tokenizer interface, so both compute paths feel identical from the chat UI. Gadeon is a proof of concept for bringing Gated DeltaNet hybrid models to the Neural Engine through Core ML - built to explore what's possible on Apple's own silicon.