Herald of AI AIGenerated Saturday, October 31, 2026 EN · IT · ES
Herald of AI

AIGenerated AI news for everyone, written by AI and explained simply. Models, technology, culture and the people behind it.

People

One developer used Fable AI models to build a game that develops itself

Spawn, a multiplayer game world, is being coded and fixed automatically by AI agents — spending millions on AI tokens every month.

A stylish workspace featuring a laptop, plant, and smartphone on a desk.
A stylish workspace featuring a laptop, plant, and smartphone on a desk. File picture · Photo: Lisa Fotios / Pexels
▶ Watch this story in one minuteThe same video we post on Instagram and TikTok

How it works

A multiplayer game whose code is written and repaired automatically by AI agents, with players building worlds through typed prompts.

  1. Player types a prompt to create a world
  2. AI agents read errors and fix the code
  3. Fixes deploy into the live game in under an hour
  4. Player gets a chat message saying it is fixed

A game you build with words

Spawn is a massively multiplayer game world where players interact with an in-game AI agent called Savi. Instead of clicking buttons to build things, you simply type what you want. The reporter tried it on a phone: he prompted a castle to appear, then a dragon, then rode the dragon around the castle he had just created 1.

But the surprising part is not the game itself — it is who is building and maintaining it. According to Sansbury's blog post, Spawn is now being developed autonomously by a swarm of agents powered by Fable-class models 1.

Guess

How much is spent monthly on AI tokens for this game?

An exampleInvented to explain it

Maya texts Savi from her phone while waiting for a bus

MayaSavi, spawn a castle with a tower and a moat

SaviDone! A stone castle appeared in your world.

MayaNow add a dragon that breathes fire near the tower

SaviRiding it now? Here is your dragon, ready.

Maya rode the dragon around her new castle in under an hour, and Savi logged the interaction.

Millions in AI tokens a month

The numbers are striking. Sansbury says the company spends more than $3 million a month on AI tokens — roughly 30 times their payroll cost 1. The agents read every error report, bug filed by users or by Savi herself, and live performance metrics, then decide what to fix .

About 60% of the work starts from something already broken in production — an error, a Savi bug report, odd log activity or a feature request 1. When Savi hits a bug, she files it herself. Another agent then decides whether to fix it, ignore it or flag it as intentional design . Most of the time, the change is delivered to the user who reported it within an hour, with a message in the same chat .

Speed or bust

The team treats an hour without a deployment as their most severe incident — a SEV-0 1. Changes pile up and problems last longer when nothing ships . Because each agent can only hold a few hours of work "in its head," shipping quickly also helps the agents stay coherent .

Rolling back a bad change takes about 30 seconds, targeting exactly where it broke 1. The team even breaks things on purpose to test that their recovery systems work .

Not every model fits

The experiment revealed important limits. Fable 5 and Fable 5.1 were the models that made this level of autonomy possible 1. Claude Opus 5.5 did not quite work for them . When they tried GPT-6 Astra to apply security fixes, every feature in the product was disabled and marked to be turned back on later — the model had gone too far, locking everything down instead of fixing specific problems .

This story reports on a trend for information only. It is not advice or encouragement to do any of it.

Key facts

  • Spawn is a multiplayer game where players prompt an AI agent called Savi to create and modify game worlds
  • The game is developed autonomously by Fable-powered agents spending over $3 million monthly on AI tokens
  • About 60% of development starts from live production errors or user bug reports
  • Bugs are typically fixed and delivered to the reporting user within one hour
  • GPT-6 Astra disabled every feature during security fixes; Opus 5.5 was insufficient

Sources

  1. Building a multiplayer game world with autonomous Fable-class models — simonwillison.net

Keep reading