Skim Recap
Recaps what you skipped and explains where you get stuck
What it does
Flick through an article too fast and Skim Recap hands the skipped passage back in a card beside your cursor. If a term stops you, select the word or phrase and press Feynman: Gemma uses the surrounding paragraph, nearby context, heading, and page title to explain what it means here. Everything runs locally through LiteRT-LM and WebGPU—no account or hosted LLM API.
Skim Recap catches what you scrolled past and summarizes skipped passages on-device with Gemma 4 E4B through LiteRT-LM.
Flick past a paragraph faster than you can read it and Skim Recap hands that passage back — a short recap beside your cursor, written by Gemma 4 running on your own GPU. Nothing you read leaves the browser. Skim Recap is a Chrome extension that detects fast scroll gestures, estimates the passage you skipped, and displays a compact recap beside your cursor using Gemma 4 E4B through LiteRT-LM. It is designed for long articles, documentation, essays, and research posts where you want to skim quickly without losing the thread of the page. The extension runs from a small popup with an enabled toggle, an adjustable flick threshold, and a model preload action. Once active, the recap panel…from skim-recap.vercel.app
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 · 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