Hyper
Perfect memory for every real-world conversation
What it does
Nearly all existing meeting tools start and end with documents. We think that's the wrong answer. You don't want enhanced notes, you just want to ask "what did we decide about pricing?" 3 weeks later and just get the answer directly. Hyper is an iOS voice AI for IRL conversations (1:1s, coffee chats, walks). One tap record, ask it anything mid-conversations with "hey hyper", or after to find answers across everything you've ever recorded. Perfect memory without files or folders or organization.
Does the same job
all alternatives →
TwinMind: AI Second Brain for Mobile2025 · ▲228Remember meetings, lectures, or your entire life for free
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, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
