Why do LLM pelicans look like this?
Design Creativity Bench finds frontier models lag human designers, with GPT-6 Astra scoring 65.5 versus 92.3.
Stories per day · 30 days
4 stories, newest first · one card per story
Stories tagged #creativity
Reinforcing Agentic Creativity in Scientific Ideation with Night Science
AI Night-Scientist uses GRPO to train LLMs for more diverse, higher-impact scientific ideas than temperature sampling.
Reinforcing Agentic Creativity in Scientific Ideation with Night Science
AI Night-Scientist uses GRPO to make LLM scientific ideation more diverse, original, and higher impact.
AI Doesn't Mean the End of Mathematics—at Least Not Yet
Schneier and Rafi argue frontier AI models produce notable mathematical results but cannot yet build genuinely new conceptual frameworks.
3