Prompting Fable 5.1 to 'grow a garden' from audio yields mycelium, rivers and fog
repligate · x · 2026-09-05
User Lariisland ran a playful generation experiment: asking a model to "grow things from an audio stream." They wanted a garden; Fable 5.1 produced roots, mycelium, rivers, and fog instead — and the model won.
Repligate, sharing the post, notes that the imagery the model reaches for (gradients, water carving paths for future water) differs strikingly from childhood-human intuitions like buildings, maps, and creatures made of materials — a reminder that some "obvious" associations aren't universal. A neat demo of the model's distinct aesthetic leanings.
Related event: Fable 5.1 grows roots and rivers from live audio streams(2 posts)→
More from Fun
- First-ever in-body prime editing treatment injected into a human — basedjensen · 2026-10-23
- AI Twitter drama: DeepSeek superfan blocked by scaling01 over model lore spat — teortaxesTex · 2026-10-23
- Run Lola Run director Tom Tykwer uses Seedance in hybrid AI filmmaking experiment — Uncanny_Harry · 2026-10-23
- "Still Worth Something" S01E01: a Pixar-style fully AI-animated comedy short — LPGroves · 2026-10-23
- Halloween AI short: "Careful who you bring home" — glagolef · 2026-10-23
- Dev builds a VST synth with Codex and MCP, lets the AI jam in his studio — Yamapama · 2026-10-23