Visually Precise AI Tutoring on iOS
Knowable is an AI tutor app for students. Point your iPhone, iPad, or Mac camera at any textbook or worksheet and Milo coaches you through every subject in real time, without just handing over the answer.
In plain words
Knowable is an AI tutoring app for iOS and Mac that helps students learn by pointing their device camera at textbooks or worksheets. The app's AI tutor, Milo, guides students through problems in real time across all subjects without simply providing answers. Using device cameras, Knowable tracks what students are working on and creates personalized lessons with explanations, worked examples, and exercises matched to each student's level. It monitors study habits and performance by topic to provide targeted support.
written from the facts on this page · September 2026
From the sources
Using specialized hardware available on recent MacBooks or iPhones, we’re able to see what’s on your page as you do the work. Yeah, other AI platforms exist. But nobody else offers you the ability to just write without needing to constantly remind the chatbot about what you’re working on. Milo writes personalized lessons from your own practice — explanation, worked examples, and exercises pitched at your level. You slipped on the sign of c in last week’s drills — remember: x² + bx + c factors into two numbers that multiply to c and add to b. Study habits, competence by topic, and every problem practiced — shareable with a parent or teacher. Every reply is a guiding question — you reach the…from useknowable.ai
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com