Extropy
OSS engine that simulates population reacting to events
What it does
Extropy builds representative synthetic populations and simulates how they react to real-world events. Every agent reasons individually from their own finances, job, commute, politics, and social network. We just published two studies: simulating Americans through a US-Iran war, and predicting the 2026 House midterms benchmarked against Kalshi. Open source. Define a scenario, build a population, run the simulation.
Does a similar job
all alternatives →
- GBGenetic Boids Web Simulation2025 · attentionmech.github.io · ▲158
- TTText to 3D simulation on a map (does history pretty well)2025 · mused.com · ▲72
Simulate anything on a map from a text prompt -- and conduct risk analysis against LiveUA map's global realtime data points from social media and news sources. I trained a GPT-2-size model on historical incident data used to predict things that will go wrong. As historian Benjamin Breen mentions, the leading language models are good historians, so the application will simulate historical events pretty well also. I include a Multi-Agent RL Urban Mobility model in progress displayed on the map as small white cubes representing traffic and pedestrians. Around SF, it uses real census data and…
- DTDecided to play god this morning, so I built an agent civilisationFeb 2026 · github.com · ▲51
at a pub in london, 2 weeks ago - I asked myself, if you spawned agents into a world with blank neural networks and zero knowledge of human existence — no language, no economy, no social templates — what would they evolve on their own? would they develop language? would they reproduce? would they evolve as energy dependent systems? what would they even talk about? so i decided to make myself a god, and built WERLD - an open-ended artificial life sim, where the agent's evolve their own neural architecture. Werld drops 30 agents onto a graph with NEAT neural networks that evolve their own…
- TPThe Probability Times2024 · theprobabilitytimes.com · ▲20
Hey HN! The idea for this started when I came across the election forecast of FiveThirthyEight [1]. They show a 1000 different possible election outcomes - each one possible. In this newspaper homepage, I try to turn these simulations into reality by feeding AI with as much detailed information about a simulation as I can (e.g. voting results per state). See source code here [2]. The whole process is explained in more depth in my blog post: https://nerology.substack.com/p/how-i-made-the-probability-t... [1]…
- ABA browser-based evolutionary simulation with emergent behaviorJan 2026 · soupof.life · ▲6
I’ve been working on a browser-based evolutionary simulation as a personal experiment. Organisms adapt to environmental pressure over time, and there are no explicit goals or scoring, the system is open-ended and runs continuously. I built this mainly to challenge myself and to explore how to surface simulation behavior and statistics in a way that stays readable rather than overwhelming. As a side effect, it’s also something my kids enjoys watching run. Curious what resonates and what doesn’t, and happy to answer questions about the design or tradeoffs.
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 · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d 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 · 28d ago · cactuscompute.com
