Fable 5.2 runs autonomously for 24 hours straight to build a complete game level
victormustar · x · 2026-11-13
Developer victormustar tested Fable 5.2, calling it excellent at long autonomous tasks (though weaker at back-and-forth human interaction). Asked to "make a real level for this game," the model worked autonomously for 24 hours straight — he forgot about it and eventually had to tell it to stop. A playable demo is online (slow, since his quota got exhausted). His take: we'll have this running locally before too long.
Related event: Fable 5.2 Works Autonomously for 24 Hours Building a Game Level(2 posts)→
More from Models
- InferenceBench: agents beat vLLM defaults but lose to simple hyperparameter search — maksym_andr · 2026-11-13
- Inkling joins Eval³ leaderboard that scores models on auditing evals for reward hacks — simonguozirui · 2026-11-13
- MiniMax H3 outputs silently changed: same workflow now yields flickering artifacts — Cequejedisestvrai · 2026-11-13
- Claude Starts Refusing to Help with Pokémon ROM Hacks and Fan-Game Development — Lucas_Zxc2833 · 2026-11-13
- Orchestrator rolls out to Pro subs, pairing Hydrogen and Argon to save quota — clmt · 2026-11-13
- Liquid AI's LFM hits 'college graduate' intelligence at 120 tps on a MacBook Pro — JosephJacks_ · 2026-11-13