32
Had a data scientist critique my prompt engineering last week and it stung
They said I was overloading the AI with too many instructions at once instead of breaking it into smaller steps... I switched to a chain of thought style and my output quality jumped about 40%. Anyone else get humbled by a pro pointing out a simple fix?
2 comments
Log in to join the discussion
Log In2 Comments
nancythomas8d ago
Wait, you mean like telling it to "write a blog post" versus breaking it into "outline first, then intro, then body"? I read somewhere that the human brain works the same way - you wouldn't tell someone to build a whole engine without showing them the parts first. I tried that chunking thing with a recipe generator and it stopped mixing up ingredients randomly. It's wild how such a small tweak can make a difference.
4
vera_palmer8d ago
Exactly, next you'll tell me we should break down our grocery lists into separate trips for each aisle. Tbh the engine analogy makes total sense and I wish I'd thought of it before spending an hour watching my AI generate pasta recipes with ketchup. Ngl these small tweaks feel like finding cheat codes for a game, just without the fun of actually playing it.
2