GPT-5.6 Sol Completes a Peaceful Factorio Run
A Hacker News experiment author reports that GPT-5.6 Sol, running in Codex at a low thinking level, completed a peaceful Factorio run lasting 13.5 hours of game time. A Python game manager and small library let the model interact with the game while enforcing GUI-equivalent restrictions such as player reach and fog of war. The author says late-game scaling problems slowed Sol, which repeatedly ferried supplies between disconnected production systems to reach the rocket launch.
The recorded run provides a concrete demonstration of GPT-5.6 Sol’s ability to sustain a long autonomous game task, while the reported scaling failures and improvised logistics delimit the achievement.
Edit: Woah, this took off! If you want more details you can subscribe at the bottom of the post or on YouTube. I’m working on a more detailed highlights/commentary post and video.
Previously: We got Claude Code playing Factorio, Towards beating Factorio autonomously, and Faketorio: an agent testbed
I got GPT-5.6 Sol, running in Codex with low thinking level, to complete a peaceful (i.e. no biters) Factorio run in 13.5 hours of game time:

A timelapse of the full run is available on YouTube.
Similar to my previous post, this run used a game manager to allow Sol/Codex to interact with the game via a small library (though in this run it was Python rather than Bash). The library allows the model to play the game programmatically while enforcing the same restrictions that human players face when using the GUI (e.g. reach of the player, fog of war).