Planchette
AI spirit board that moves the planchette and spells answers
What it does
Planchette is an AI-powered spirit board with its own language model, no cloud APIs, no canned answers. The planchette glides across the board spelling replies letter by letter with ghost trails and dust particles. Golden glow on YES, shake on NO, cinematic fadeout on GOODBYE. 5% chance of poltergeist effects: smoke, shadow figures, spirit orbs. 6 themes, idle animations, and tarot-style shareable cards from illustrated decks.
Does the same job
all alternatives →
- G3GPT-3 powered Ouija spirit board that moves your mouse2022 · ouija.attejuvonen.fi · ▲65
Hi HN! I've been tinkering with this mini-game / horror experience for a while. I hope it creeps you out! You can go into settings to toggle between 2 different chatbots: a scripted experience (with achievements to unlock) and a more versatile GPT-3 mode. Let me know what you think! :) There's also a toggle to show how the mouse magic is made. Source is available here: https://github.com/baobabKoodaa/ouija
- IMI made an AI fortune teller to predict the future2024 · tarotread.ai · ▲18
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
