Lumi
The AI Tutor for Anything
What it does
Lumi is an interactive AI tutor for everyone. Ask a question out loud, upload your notes or a past paper, and watch the explanation get drawn on a whiteboard exactly like a real online tutor.
Lumi is an interactive AI tutor for UK A-Level and GCSE students. Talk to it out loud, upload your notes or a past paper, and watch it draw the explanation on a live whiteboard you can interrupt. Covers AQA, Edexcel, OCR and WJEC. Free to start.
Upload your notes or a past paper. Lumi draws the explanation on a live whiteboard and changes it until it clicks. Gravity pulls inward while sideways velocity keeps the planet moving past the star. A continuous fall where the surface curves away at the same rate. So the planet is always falling, it just keeps missing the star. There are lots of ways to get an answer. Far fewer that talk it through, draw what matters and change the explanation when it doesn’t click. Type it how you'd say it out loud, or drag in a PDF, a past paper or your own notes. Lumi reads them and starts from what's actually confusing you. The whiteboard fills in as Lumi talks: curves, forces, cells, mind maps. Point…from trylumi.co
Does the same job
all alternatives →
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 · 27d 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