one of the valuable types of data in the future might be inspiration for agents. hear me out. i don’t mean inspiration as in “an idea for the agent to make”. i mean inspiration the agent uses to raise its ambition and divergent creativity. the only reliable way i found to raise the creativity and ambition of llms is to give them an idea what you’re after. yes you could interject and state “duh lol bro that’s just few shot prompting”, but few-shot prompts were meant to solve output shape (same as fine-tuning). and sure, you might already do some of this naturally in your prompting, but developing an intuition which exact combination of curated examples lead to superior results isn’t trivial. the datasets needed are creative sparks that force the agent to think bigger and better. if you tell an agent “design me an editorial yearly recap of my e-commerce platform”, I guarantee that it won’t arrive at an idea (and execution, but that’s a different problem) as powerful as shopify’s winter editions site. but if you give it enough truly extraordinary examples, it will raise its own ambition. crucially, these creative sparks don’t have to come from the same niche. in fact, it’s often better they don’t. but calibrating these datasets and how and when to employ them is not obvious, and itself requires human creativity llms do not possess (yet). i suspect this is a entire new job category we’ll soon see manifest, distinct from prompt engineering, or perhaps an evolution of it: ‘idea guys’, interior designers, curators, tastemakers, will find jobs in tech startups curating these creative spark datasets. there is so much value, and thus money to be made building these creative engines. exciting times!