Building a multiplayer game world with autonomous Fable-class models
- ID
- 40824
- Status
- summarized
- Published
- 30 Oct 2026, 1:00 AM
- Fetched
- 30 Oct 2026, 6:52 AM
- Provider
- Simon Willison
- Category
- developer-ai
- Original URL
- https://simonwillison.net/2026/Oct/29/how-i-built-the-most-ai-pilled-company-in-the-world/
- Source URL
- https://simonwillison.net/atom/everything/
Summary
- Score
- 8.0
- Created
- 30 Oct 2026, 6:52 AM
- Tags
- Audience
- developersvibe_codersai_ml_learnersai_agent_userssaas_founders
What happened
Jacob Sansbury's write-up on Spawn describes a massively multiplayer game world where players prompt an in-game agent, Savi, to change the world — Simon Willison spawned a castle and a dragon and rode it, from his phone. Sansbury says Spawn is now largely built by a swarm of Fable-powered agents burning over $3 million in tokens per month, shipping to production hourly, with about 60% of work starting from a production error, a Savi-filed bug, a log anomaly, or a feature request. An hour without a ship is treated as a SEV-0, broken changes roll back in 30 seconds, and the model choice matters: Fable 5 then 5.1 made the autonomy possible, Opus 5.5 'doesn't quite hack it', and GPT-6 Astra, asked to apply security-review fixes, disabled every feature to make the product secure.
Why it matters
This is a concrete cost and cadence data point for anyone building agent loops: $3M+/month in tokens, hourly deploys, 30-second scoped rollback, and a policy that treats an unshipped hour as SEV-0. Two decisions it should force: (1) measure your token spend per shipped change before copying this cadence, because the economics only work if agent output converts to production changes; (2) treat model swaps as capability changes, not drop-in upgrades — Opus 5.5 reportedly couldn't sustain the loop, and GPT-6 Astra turned a security review into disabling every feature, so run agent-driven security fixes against a staging copy with an explicit 'don't disable functionality' constraint.
Discussion angle
Hourly auto-shipping only works because a game tolerates fast rollback — so what is the smallest surface in your own product where you'd let agents ship unattended, and what would 'an hour without a ship is SEV-0' actually cost your team in review time?