FluffyPoly
Trade prediction market With Tactical Agents
What it does
FluffyPoly was constructed to solve a specific problem: continuous, unsleeping participation in prediction markets. Human traders require rest, suffer from emotional tilt, and cannot process raw exchange data 24/7 without fatigue.
Does the same job
all alternatives →- CYCreate your own prediction market in two minutes2022 · manifold.markets · ▲84
Hi HN! Excited to show off the project we've been working on for the last couple months. We started with an idea for a crazy twist on prediction markets: You come up with a question for traders to predict, and then decide the outcome yourself. For example, you could create a market on “Will my date with [X] go well?” Anyone can bet on it, and the bets create a forecast on the chance your date goes well. After the date is over, you get to judge the result and reward the traders who picked the correct side. There are so many ways for this mechanism to go wrong: the creator of the market can be…
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
