Chunks Microlearning
Replace doomscrolling with 5-minute learning
What it does
Hi all. I built Chunks because I was losing an hour a night to Instagram without learning anything. I tried Nibble and Paladin but they felt shallow. So I built my own. Chunks has 200+ stories across history, philosophy, science, literature, art, music and more. Each is broken into 5-10 minute chapters you can read or listen to. Every story is fact-checked against primary sources. Free to start.
Does the same job
all alternatives →- IVI've been writing daily TILs for a year2016 · github.com · ▲819
- IBI built an app to organize fragmented learning2025 · apps.apple.com · ▲5
Hi HN, I built an app to solve a problem I kept running into: I’d read great articles or watch insightful YouTube videos, but within a few days, I’d forget most of what I learned. Taking detailed notes felt like a chore, and I'd rarely revisit them anyway. To solve my own problem, I built Curio. It's an iOS app designed for low-effort capture and active recall. How it works: 1. Share any article or YouTube link to the app. 2. It automatically extracts key ideas as bullet points and links them back to the original context (the specific paragraph or timestamp). 3. The app then generates…
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, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
