Lila Sciences Proposes Creative Priming to Break AI's Creative Paradox
LilaSciences · hf · 2026-11-11
Lila Sciences (authors include open-endedness luminaries Kenneth O. Stanley and Joel Lehman) released a paper on creative priming (CP).
- Problem: creativity faces a creative paradox — learning to repeat past examples of creative success makes those examples recur, inhibiting the very creativity desired.
- Approach: treat creativity as an explicit process rather than a property of artifacts; a priming model trained with GRPO generates prompt-specific primers that assist a response model, decoupling the creative process from response generation to produce novel, high-quality, diverse outputs.
- Paper and model are up on Hugging Face.
More from Research
- MKA deep dive: top models cluster at 95-97% on basics but split 28-57% on hard tasks — ArtificialAnlys · 2026-11-11
- MKA Benchmark by Output Type: No Model Tops 52% on Word or Text Files — ArtificialAnlys · 2026-11-11
- MKA Vertical Results: No Single Model Dominates Across 10 Industries — ArtificialAnlys · 2026-11-11
- Google DeepMind Launches MKA Benchmark: One Task Cost Claude $68 Across 224 Turns — ArtificialAnlys · 2026-11-11
- DeepMind-backed MKA benchmark crowns Claude Fable 5.2 at 57%, with 30x cost spread — ArtificialAnlys · 2026-11-11
- Emergent misalignment is predictable OOD; later-layer fine-tuning reduces transfer — AdtRaghunathan · 2026-11-11