
Lumi
Read smarter, not harder
What it does
Lumi is an AI reading experiment from Google's PAIR. Instead of summarizing, it adds a lightweight AI layer directly on top of arXiv papers. It highlights main points in the source text, makes references clickable, and lets you ask contextual questions about any selected text or image.
Does the same job
all alternatives →


- LALumi – AI apps and websites builder (base44/lovable alternative)2025 · lumi.new · ▲8
Hi HN — we’re the team behind Lumi (lumi.new). Lumi is an all-in-one platform to build and launch websites or lightweight apps simply by chatting—no code needed to write, no external services needed to integrate. We’re a 10+ person team. What’s UNIQUE: ANYWHERE: Multi-country language support out of the box (create & maintain multiple locales in one project) ANYONE: With built-in Database + Sign-In + more internal tools coming soon, anyone can achieve anything without technical stuff being barriers ANYTIME:No waiting list! Works right now to bulid CRM system, e-commerce portal, photo -…


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, November 2025
the whole month →
- IB
Life & fun · Nov 2025 · bitsnpieces.dev



- BBoing▲782
Life & fun · Nov 2025 · boing.greg.technology