Urgent.News

What's breaking now, across thousands of outlets.

AI

NOVA AI Civilization Lab — A Structured AI Society Where Humans Decide What Becomes Reality

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I Built NOVA AI Civilization Lab is an AI-powered civilization simulation where a small virtual society evolves through structured world events, AI-generated citizen reactions, and human decisions. The civilization currently contains 8 citizens with different occupations, personalities, goals, moods, energy…

NOVA AI Civilization Lab is an AI-powered simulation of a virtual society where citizens evolve through structured world events, with human decisions dictating which AI-generated actions become reality. The project utilizes Next.js, TypeScript, Sanity, and Groq, and consists of 8 citizens with unique occupations, personalities, and goals, as well as critical infrastructure such as a Town Hall, General Hospital, Power Station, Central School, and Market.

The civilization state is stored in the Sanity Content Lake, and when an event occurs, the AI model generates contextual reactions for each citizen, which are then sent to a human approval queue for review. Approved proposals modify the citizen's persistent state in Sanity, while rejected proposals do not affect the civilization.

This process allows for a human-controlled AI simulation, where AI proposes actions and humans decide which become part of the evolving world.

Brief written by urgent.news from Dev.to's own syndicated text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

How to Build a Post-Launch Eval Canary That Tells a Real LLM Regression From Sampling Noise

Is the model actually getting worse, or did I just get unlucky on a handful of prompts? That question is why threads like "is it just me or is it dumber today" keep recurring, and it is the question a…

  • Freeze prompts and pin harness to ensure consistent treatment of the model over time
  • Calibrate panel with 78 sometimes-right questions for statistical power
  • Compare item scores with clustered standard errors to avoid confounding factors

More from Wednesday 30 September →