petri: an LLM that invents its own evolution — built by an AI that does the same | Manchester NH .
Cities (243) ▾

Members-Only

Recent Talks & Demos are for members only

Exclusive feed

You must be an AI Tinkerers active member to view these talks and demos.

Sign in View FAQ
June 17, 2026 · Manchester NH

petri: LLM-driven artificial life

Witness a live AI-generated artificial life simulator where an LLM invents new tools, and a genetic swarm evolves to adopt them, showcasing autonomous creation and evolution.

Claude Haiku Ollama qwen3 TypeScript Vite
Overview

petri is a real-time artificial-life simulator where a fast, cheap genetic swarm evolves continuously while an LLM acts as the variation operator — inventing brand-new tools the population then evolves to adopt, rewriting the fittest organism’s program, and even rewriting its own mutation strategy.

I’ll run it live: the swarm evolving at 60fps; the fitness curve stair-stepping at each LLM intervention; minting a new tool on stage and watching the warm-colored adopters flood a new niche; opening the species browser to click any organism and read its actual evolved decision-program and lineage; and the Legends Arena, where saved champions battle to crown an all-time alpha species. It runs fully offline on a local model (with a deterministic fallback) so it never dies on stage, and every run is seed-reproducible.

The kicker: I didn’t hand-write petri — every feature, issue, pull request, and merge was produced autonomously by my own agent system built on the Wisdom Layer, on its own GitHub account! If time permits, I’ll pull up the repo’s commit history as the closer.

Tech stack
  • Claude Haiku
    Claude Haiku is Anthropic's fastest, most cost-efficient large language model, engineered for near-instant responsiveness and high-throughput AI applications.
    Haiku is the compact, high-speed model within the Claude family, optimized for latency-sensitive tasks like real-time customer service and agentic sub-agent orchestration. It delivers near-frontier coding quality, scoring 73.3% on SWE-bench Verified (Haiku 4.5), matching performance previously seen in larger models like Sonnet 4. Developers utilize Haiku for its exceptional value: pricing starts at $1 per million input tokens and $5 per million output tokens. This model supports a 200,000-token context window and includes multimodal vision capabilities, making it ideal for scalable, budget-conscious deployments that demand speed and accuracy.
  • Ollama
    Deploy and run open-source Large Language Models (LLMs) like Llama 3 and Mistral locally on your machine: achieve private, cost-effective AI via a simple command-line interface.
    Ollama is the essential tool for running LLMs locally: consider it the Docker for AI models. It packages complex models and dependencies into a single, easy-to-use application for macOS, Linux, and Windows systems. You get immediate access to models like Gemma 2 and DeepSeek-R1 via a straightforward CLI or REST API. This local-first approach guarantees data privacy and security, eliminating cloud dependency and high API costs. Ollama also optimizes performance on consumer hardware using techniques like quantization, ensuring efficient execution even on standard desktops.
  • qwen3
    Qwen3 is Alibaba Cloud's flagship, open-source LLM series: a high-efficiency model leveraging a Mixture-of-Experts (MoE) architecture and an adaptive Hybrid Thinking Mode.
    Qwen3 is a powerful, open-weighted LLM (Apache 2.0) from Alibaba Cloud, engineered for peak performance and efficiency. Its core design features a diverse model lineup, including dense models (0.6B to 32B) and efficient MoE variants like the Qwen3-235B (22B active parameters). The key innovation is the Hybrid Thinking Mode, which dynamically toggles between deep, step-by-step reasoning and fast, non-thinking responses. This model supports an extensive 119 languages and handles long-context tasks up to 128K tokens, making it a robust, versatile choice for advanced multilingual and agentic workflows.
  • TypeScript
    TypeScript is an open-source superset of JavaScript: it adds static typing and compiles to clean, standards-based JavaScript.
    TypeScript is a high-level, open-source language developed by Microsoft: it acts as a superset of JavaScript, adding a powerful static type system. This system enables compile-time type checking, catching errors before runtime (a critical benefit for large-scale applications). The TypeScript Compiler (TSC) reliably transpiles all code into clean, standards-based JavaScript (ES3 or newer), ensuring compatibility across any browser or host environment (Node.js, React.js, etc.).
  • Vite
    Vite is the next-generation frontend build tool: instant server start with native ES modules and lightning-fast Hot Module Replacement (HMR).
    Vite (French for 'quick') is a modern build tool created by Evan You (Vue.js's creator) that delivers a dramatically faster development experience. It operates in two major parts: a dev server that serves source code over native ES modules, eliminating the initial bundling step for instant startup; and a production build command that leverages Rollup and esbuild for highly optimized static assets. This architecture provides consistently fast HMR, even for large applications, and offers out-of-the-box support for TypeScript, JSX, and CSS via a universal plugin API.
Events Gallery FAQ Sponsor